Spaces:

iteratehack
/

neuro-flyt-training

Configuration error

neuro-flyt-training / train_log_500k.txt

Antigravity Agent

Deploy Neuro-Flyt 3D Training

ae22fc1 13 days ago

83.7 kB

	Setting up Training Environment...
	Creating Liquid PPO Agent...
	Using cpu device
	Wrapping the env with a `Monitor` wrapper
	Wrapping the env in a DummyVecEnv.
	Starting Training (This may take a while)...
	----------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.56e+04 \|
	\| time/ \| \|
	\| fps \| 608 \|
	\| iterations \| 1 \|
	\| time_elapsed \| 3 \|
	\| total_timesteps \| 2048 \|
	----------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.23e+04 \|
	\| time/ \| \|
	\| fps \| 177 \|
	\| iterations \| 2 \|
	\| time_elapsed \| 23 \|
	\| total_timesteps \| 4096 \|
	\| train/ \| \|
	\| approx_kl \| 0.0049500195 \|
	\| clip_fraction \| 0.0341 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.67 \|
	\| explained_variance \| -9.31e-05 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.15e+05 \|
	\| n_updates \| 10 \|
	\| policy_gradient_loss \| -0.00313 \|
	\| std \| 0.999 \|
	\| value_loss \| 1.99e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.19e+04 \|
	\| time/ \| \|
	\| fps \| 129 \|
	\| iterations \| 3 \|
	\| time_elapsed \| 47 \|
	\| total_timesteps \| 6144 \|
	\| train/ \| \|
	\| approx_kl \| 0.002073763 \|
	\| clip_fraction \| 0.00542 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.67 \|
	\| explained_variance \| 2.62e-05 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 5.71e+04 \|
	\| n_updates \| 20 \|
	\| policy_gradient_loss \| -0.000381 \|
	\| std \| 0.996 \|
	\| value_loss \| 1.15e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.28e+04 \|
	\| time/ \| \|
	\| fps \| 116 \|
	\| iterations \| 4 \|
	\| time_elapsed \| 70 \|
	\| total_timesteps \| 8192 \|
	\| train/ \| \|
	\| approx_kl \| 0.0047560623 \|
	\| clip_fraction \| 0.0275 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.64 \|
	\| explained_variance \| 8.34e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 7.31e+04 \|
	\| n_updates \| 30 \|
	\| policy_gradient_loss \| -0.00268 \|
	\| std \| 0.988 \|
	\| value_loss \| 1.42e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.4e+04 \|
	\| time/ \| \|
	\| fps \| 93 \|
	\| iterations \| 5 \|
	\| time_elapsed \| 109 \|
	\| total_timesteps \| 10240 \|
	\| train/ \| \|
	\| approx_kl \| 0.004183922 \|
	\| clip_fraction \| 0.0234 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.62 \|
	\| explained_variance \| -4.77e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.35e+05 \|
	\| n_updates \| 40 \|
	\| policy_gradient_loss \| -0.003 \|
	\| std \| 0.985 \|
	\| value_loss \| 2.21e+05 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.28e+04 \|
	\| time/ \| \|
	\| fps \| 98 \|
	\| iterations \| 6 \|
	\| time_elapsed \| 125 \|
	\| total_timesteps \| 12288 \|
	\| train/ \| \|
	\| approx_kl \| 0.005293761 \|
	\| clip_fraction \| 0.0418 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.61 \|
	\| explained_variance \| -3.58e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.32e+05 \|
	\| n_updates \| 50 \|
	\| policy_gradient_loss \| -0.00347 \|
	\| std \| 0.985 \|
	\| value_loss \| 2.86e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.41e+04 \|
	\| time/ \| \|
	\| fps \| 97 \|
	\| iterations \| 7 \|
	\| time_elapsed \| 146 \|
	\| total_timesteps \| 14336 \|
	\| train/ \| \|
	\| approx_kl \| 0.0050999783 \|
	\| clip_fraction \| 0.0295 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.59 \|
	\| explained_variance \| -7.15e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 4.66e+04 \|
	\| n_updates \| 60 \|
	\| policy_gradient_loss \| -0.00355 \|
	\| std \| 0.974 \|
	\| value_loss \| 8.14e+04 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.6e+04 \|
	\| time/ \| \|
	\| fps \| 103 \|
	\| iterations \| 8 \|
	\| time_elapsed \| 158 \|
	\| total_timesteps \| 16384 \|
	\| train/ \| \|
	\| approx_kl \| 0.0042739166 \|
	\| clip_fraction \| 0.0147 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.57 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.64e+05 \|
	\| n_updates \| 70 \|
	\| policy_gradient_loss \| -0.0019 \|
	\| std \| 0.972 \|
	\| value_loss \| 3.31e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.7e+04 \|
	\| time/ \| \|
	\| fps \| 108 \|
	\| iterations \| 9 \|
	\| time_elapsed \| 170 \|
	\| total_timesteps \| 18432 \|
	\| train/ \| \|
	\| approx_kl \| 0.0053871158 \|
	\| clip_fraction \| 0.0297 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.56 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.43e+05 \|
	\| n_updates \| 80 \|
	\| policy_gradient_loss \| -0.00304 \|
	\| std \| 0.972 \|
	\| value_loss \| 5.33e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.81e+04 \|
	\| time/ \| \|
	\| fps \| 112 \|
	\| iterations \| 10 \|
	\| time_elapsed \| 181 \|
	\| total_timesteps \| 20480 \|
	\| train/ \| \|
	\| approx_kl \| 0.0035741455 \|
	\| clip_fraction \| 0.0138 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.56 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.74e+05 \|
	\| n_updates \| 90 \|
	\| policy_gradient_loss \| -0.00138 \|
	\| std \| 0.971 \|
	\| value_loss \| 3.49e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.79e+04 \|
	\| time/ \| \|
	\| fps \| 116 \|
	\| iterations \| 11 \|
	\| time_elapsed \| 193 \|
	\| total_timesteps \| 22528 \|
	\| train/ \| \|
	\| approx_kl \| 0.004108442 \|
	\| clip_fraction \| 0.0245 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.56 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.53e+05 \|
	\| n_updates \| 100 \|
	\| policy_gradient_loss \| -0.00274 \|
	\| std \| 0.971 \|
	\| value_loss \| 5.84e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.84e+04 \|
	\| time/ \| \|
	\| fps \| 119 \|
	\| iterations \| 12 \|
	\| time_elapsed \| 205 \|
	\| total_timesteps \| 24576 \|
	\| train/ \| \|
	\| approx_kl \| 0.0057261223 \|
	\| clip_fraction \| 0.0375 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.53 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.12e+04 \|
	\| n_updates \| 110 \|
	\| policy_gradient_loss \| -0.003 \|
	\| std \| 0.96 \|
	\| value_loss \| 1.72e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.82e+04 \|
	\| time/ \| \|
	\| fps \| 122 \|
	\| iterations \| 13 \|
	\| time_elapsed \| 217 \|
	\| total_timesteps \| 26624 \|
	\| train/ \| \|
	\| approx_kl \| 0.0051155365 \|
	\| clip_fraction \| 0.0225 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.5 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.4e+05 \|
	\| n_updates \| 120 \|
	\| policy_gradient_loss \| -0.00331 \|
	\| std \| 0.955 \|
	\| value_loss \| 4.7e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.83e+04 \|
	\| time/ \| \|
	\| fps \| 125 \|
	\| iterations \| 14 \|
	\| time_elapsed \| 228 \|
	\| total_timesteps \| 28672 \|
	\| train/ \| \|
	\| approx_kl \| 0.005322621 \|
	\| clip_fraction \| 0.042 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.48 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.33e+05 \|
	\| n_updates \| 130 \|
	\| policy_gradient_loss \| -0.00404 \|
	\| std \| 0.952 \|
	\| value_loss \| 2.58e+05 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.78e+04 \|
	\| time/ \| \|
	\| fps \| 127 \|
	\| iterations \| 15 \|
	\| time_elapsed \| 240 \|
	\| total_timesteps \| 30720 \|
	\| train/ \| \|
	\| approx_kl \| 0.006120109 \|
	\| clip_fraction \| 0.0588 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.46 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.32e+05 \|
	\| n_updates \| 140 \|
	\| policy_gradient_loss \| -0.00445 \|
	\| std \| 0.942 \|
	\| value_loss \| 2.73e+05 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.79e+04 \|
	\| time/ \| \|
	\| fps \| 129 \|
	\| iterations \| 16 \|
	\| time_elapsed \| 253 \|
	\| total_timesteps \| 32768 \|
	\| train/ \| \|
	\| approx_kl \| 0.004814163 \|
	\| clip_fraction \| 0.0178 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.43 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 5.79e+04 \|
	\| n_updates \| 150 \|
	\| policy_gradient_loss \| -0.000932 \|
	\| std \| 0.939 \|
	\| value_loss \| 1.42e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.82e+04 \|
	\| time/ \| \|
	\| fps \| 130 \|
	\| iterations \| 17 \|
	\| time_elapsed \| 266 \|
	\| total_timesteps \| 34816 \|
	\| train/ \| \|
	\| approx_kl \| 0.0027875581 \|
	\| clip_fraction \| 0.0163 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.43 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.62e+05 \|
	\| n_updates \| 160 \|
	\| policy_gradient_loss \| -0.00144 \|
	\| std \| 0.94 \|
	\| value_loss \| 3.25e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.84e+04 \|
	\| time/ \| \|
	\| fps \| 132 \|
	\| iterations \| 18 \|
	\| time_elapsed \| 277 \|
	\| total_timesteps \| 36864 \|
	\| train/ \| \|
	\| approx_kl \| 0.0035902325 \|
	\| clip_fraction \| 0.0154 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.43 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.59e+05 \|
	\| n_updates \| 170 \|
	\| policy_gradient_loss \| -0.00172 \|
	\| std \| 0.942 \|
	\| value_loss \| 3.88e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.83e+04 \|
	\| time/ \| \|
	\| fps \| 134 \|
	\| iterations \| 19 \|
	\| time_elapsed \| 289 \|
	\| total_timesteps \| 38912 \|
	\| train/ \| \|
	\| approx_kl \| 0.0044348813 \|
	\| clip_fraction \| 0.025 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.44 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.36e+05 \|
	\| n_updates \| 180 \|
	\| policy_gradient_loss \| -0.00187 \|
	\| std \| 0.943 \|
	\| value_loss \| 2.4e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.77e+04 \|
	\| time/ \| \|
	\| fps \| 136 \|
	\| iterations \| 20 \|
	\| time_elapsed \| 300 \|
	\| total_timesteps \| 40960 \|
	\| train/ \| \|
	\| approx_kl \| 0.003115609 \|
	\| clip_fraction \| 0.0162 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.42 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.02e+05 \|
	\| n_updates \| 190 \|
	\| policy_gradient_loss \| -0.00152 \|
	\| std \| 0.936 \|
	\| value_loss \| 2.02e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.72e+04 \|
	\| time/ \| \|
	\| fps \| 136 \|
	\| iterations \| 21 \|
	\| time_elapsed \| 314 \|
	\| total_timesteps \| 43008 \|
	\| train/ \| \|
	\| approx_kl \| 0.0044121114 \|
	\| clip_fraction \| 0.0311 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.42 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 4.9e+04 \|
	\| n_updates \| 200 \|
	\| policy_gradient_loss \| -0.00261 \|
	\| std \| 0.941 \|
	\| value_loss \| 1.09e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.69e+04 \|
	\| time/ \| \|
	\| fps \| 138 \|
	\| iterations \| 22 \|
	\| time_elapsed \| 326 \|
	\| total_timesteps \| 45056 \|
	\| train/ \| \|
	\| approx_kl \| 0.0050966754 \|
	\| clip_fraction \| 0.0294 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.41 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 5.13e+04 \|
	\| n_updates \| 210 \|
	\| policy_gradient_loss \| -0.00221 \|
	\| std \| 0.933 \|
	\| value_loss \| 1.11e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.71e+04 \|
	\| time/ \| \|
	\| fps \| 139 \|
	\| iterations \| 23 \|
	\| time_elapsed \| 337 \|
	\| total_timesteps \| 47104 \|
	\| train/ \| \|
	\| approx_kl \| 0.0042023044 \|
	\| clip_fraction \| 0.0154 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.4 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 5.53e+04 \|
	\| n_updates \| 220 \|
	\| policy_gradient_loss \| -0.000932 \|
	\| std \| 0.934 \|
	\| value_loss \| 1.32e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.74e+04 \|
	\| time/ \| \|
	\| fps \| 140 \|
	\| iterations \| 24 \|
	\| time_elapsed \| 348 \|
	\| total_timesteps \| 49152 \|
	\| train/ \| \|
	\| approx_kl \| 0.0060270163 \|
	\| clip_fraction \| 0.0548 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.4 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.27e+05 \|
	\| n_updates \| 230 \|
	\| policy_gradient_loss \| -0.00514 \|
	\| std \| 0.932 \|
	\| value_loss \| 2.93e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.77e+04 \|
	\| time/ \| \|
	\| fps \| 141 \|
	\| iterations \| 25 \|
	\| time_elapsed \| 361 \|
	\| total_timesteps \| 51200 \|
	\| train/ \| \|
	\| approx_kl \| 0.003641401 \|
	\| clip_fraction \| 0.0161 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.4 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.7e+05 \|
	\| n_updates \| 240 \|
	\| policy_gradient_loss \| -0.00216 \|
	\| std \| 0.937 \|
	\| value_loss \| 3.48e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.79e+04 \|
	\| time/ \| \|
	\| fps \| 142 \|
	\| iterations \| 26 \|
	\| time_elapsed \| 372 \|
	\| total_timesteps \| 53248 \|
	\| train/ \| \|
	\| approx_kl \| 0.0040730843 \|
	\| clip_fraction \| 0.0225 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.41 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.05e+05 \|
	\| n_updates \| 250 \|
	\| policy_gradient_loss \| -0.00147 \|
	\| std \| 0.934 \|
	\| value_loss \| 4.28e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.8e+04 \|
	\| time/ \| \|
	\| fps \| 143 \|
	\| iterations \| 27 \|
	\| time_elapsed \| 384 \|
	\| total_timesteps \| 55296 \|
	\| train/ \| \|
	\| approx_kl \| 0.003144626 \|
	\| clip_fraction \| 0.00791 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.42 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.71e+05 \|
	\| n_updates \| 260 \|
	\| policy_gradient_loss \| -0.00195 \|
	\| std \| 0.94 \|
	\| value_loss \| 3.93e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.83e+04 \|
	\| time/ \| \|
	\| fps \| 144 \|
	\| iterations \| 28 \|
	\| time_elapsed \| 397 \|
	\| total_timesteps \| 57344 \|
	\| train/ \| \|
	\| approx_kl \| 0.0052720373 \|
	\| clip_fraction \| 0.0272 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.42 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.75e+05 \|
	\| n_updates \| 270 \|
	\| policy_gradient_loss \| -0.00242 \|
	\| std \| 0.935 \|
	\| value_loss \| 3.07e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.79e+04 \|
	\| time/ \| \|
	\| fps \| 145 \|
	\| iterations \| 29 \|
	\| time_elapsed \| 409 \|
	\| total_timesteps \| 59392 \|
	\| train/ \| \|
	\| approx_kl \| 0.0041839215 \|
	\| clip_fraction \| 0.0244 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.4 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.79e+05 \|
	\| n_updates \| 280 \|
	\| policy_gradient_loss \| -0.00283 \|
	\| std \| 0.933 \|
	\| value_loss \| 3.86e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.8e+04 \|
	\| time/ \| \|
	\| fps \| 145 \|
	\| iterations \| 30 \|
	\| time_elapsed \| 421 \|
	\| total_timesteps \| 61440 \|
	\| train/ \| \|
	\| approx_kl \| 0.0053371564 \|
	\| clip_fraction \| 0.0308 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.35 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 3.19e+04 \|
	\| n_updates \| 290 \|
	\| policy_gradient_loss \| -0.00282 \|
	\| std \| 0.915 \|
	\| value_loss \| 6.26e+04 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.78e+04 \|
	\| time/ \| \|
	\| fps \| 146 \|
	\| iterations \| 31 \|
	\| time_elapsed \| 433 \|
	\| total_timesteps \| 63488 \|
	\| train/ \| \|
	\| approx_kl \| 0.0045930664 \|
	\| clip_fraction \| 0.0416 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.31 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.66e+05 \|
	\| n_updates \| 300 \|
	\| policy_gradient_loss \| -0.00376 \|
	\| std \| 0.913 \|
	\| value_loss \| 3.15e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.77e+04 \|
	\| time/ \| \|
	\| fps \| 147 \|
	\| iterations \| 32 \|
	\| time_elapsed \| 445 \|
	\| total_timesteps \| 65536 \|
	\| train/ \| \|
	\| approx_kl \| 0.006433362 \|
	\| clip_fraction \| 0.0423 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.29 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 7.14e+04 \|
	\| n_updates \| 310 \|
	\| policy_gradient_loss \| -0.00386 \|
	\| std \| 0.906 \|
	\| value_loss \| 1.45e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.74e+04 \|
	\| time/ \| \|
	\| fps \| 147 \|
	\| iterations \| 33 \|
	\| time_elapsed \| 457 \|
	\| total_timesteps \| 67584 \|
	\| train/ \| \|
	\| approx_kl \| 0.0060111308 \|
	\| clip_fraction \| 0.0567 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.27 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.6e+04 \|
	\| n_updates \| 320 \|
	\| policy_gradient_loss \| -0.004 \|
	\| std \| 0.904 \|
	\| value_loss \| 1.9e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.71e+04 \|
	\| time/ \| \|
	\| fps \| 148 \|
	\| iterations \| 34 \|
	\| time_elapsed \| 469 \|
	\| total_timesteps \| 69632 \|
	\| train/ \| \|
	\| approx_kl \| 0.002752479 \|
	\| clip_fraction \| 0.0267 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.28 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 3.72e+04 \|
	\| n_updates \| 330 \|
	\| policy_gradient_loss \| -0.000776 \|
	\| std \| 0.909 \|
	\| value_loss \| 5.9e+04 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.7e+04 \|
	\| time/ \| \|
	\| fps \| 149 \|
	\| iterations \| 35 \|
	\| time_elapsed \| 480 \|
	\| total_timesteps \| 71680 \|
	\| train/ \| \|
	\| approx_kl \| 0.004144692 \|
	\| clip_fraction \| 0.0243 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.29 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 4.48e+04 \|
	\| n_updates \| 340 \|
	\| policy_gradient_loss \| -0.00131 \|
	\| std \| 0.907 \|
	\| value_loss \| 1.06e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.69e+04 \|
	\| time/ \| \|
	\| fps \| 149 \|
	\| iterations \| 36 \|
	\| time_elapsed \| 492 \|
	\| total_timesteps \| 73728 \|
	\| train/ \| \|
	\| approx_kl \| 0.0060227686 \|
	\| clip_fraction \| 0.043 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.28 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 9.28e+04 \|
	\| n_updates \| 350 \|
	\| policy_gradient_loss \| -0.00293 \|
	\| std \| 0.903 \|
	\| value_loss \| 1.91e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.68e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 37 \|
	\| time_elapsed \| 504 \|
	\| total_timesteps \| 75776 \|
	\| train/ \| \|
	\| approx_kl \| 0.003745494 \|
	\| clip_fraction \| 0.0147 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.29 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 6.81e+04 \|
	\| n_updates \| 360 \|
	\| policy_gradient_loss \| -0.00168 \|
	\| std \| 0.91 \|
	\| value_loss \| 1.31e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.71e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 38 \|
	\| time_elapsed \| 516 \|
	\| total_timesteps \| 77824 \|
	\| train/ \| \|
	\| approx_kl \| 0.0039524576 \|
	\| clip_fraction \| 0.0286 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.3 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.13e+05 \|
	\| n_updates \| 370 \|
	\| policy_gradient_loss \| -0.00305 \|
	\| std \| 0.909 \|
	\| value_loss \| 2.44e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.67e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 39 \|
	\| time_elapsed \| 529 \|
	\| total_timesteps \| 79872 \|
	\| train/ \| \|
	\| approx_kl \| 0.005160669 \|
	\| clip_fraction \| 0.0254 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.29 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.6e+05 \|
	\| n_updates \| 380 \|
	\| policy_gradient_loss \| -0.00292 \|
	\| std \| 0.907 \|
	\| value_loss \| 2.55e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.66e+04 \|
	\| time/ \| \|
	\| fps \| 151 \|
	\| iterations \| 40 \|
	\| time_elapsed \| 540 \|
	\| total_timesteps \| 81920 \|
	\| train/ \| \|
	\| approx_kl \| 0.0046265204 \|
	\| clip_fraction \| 0.0285 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.27 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.09e+04 \|
	\| n_updates \| 390 \|
	\| policy_gradient_loss \| -0.00145 \|
	\| std \| 0.902 \|
	\| value_loss \| 3.81e+04 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.67e+04 \|
	\| time/ \| \|
	\| fps \| 151 \|
	\| iterations \| 41 \|
	\| time_elapsed \| 553 \|
	\| total_timesteps \| 83968 \|
	\| train/ \| \|
	\| approx_kl \| 0.0042863134 \|
	\| clip_fraction \| 0.0239 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.26 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 9.31e+04 \|
	\| n_updates \| 400 \|
	\| policy_gradient_loss \| -0.00143 \|
	\| std \| 0.9 \|
	\| value_loss \| 1.85e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.68e+04 \|
	\| time/ \| \|
	\| fps \| 151 \|
	\| iterations \| 42 \|
	\| time_elapsed \| 566 \|
	\| total_timesteps \| 86016 \|
	\| train/ \| \|
	\| approx_kl \| 0.005065168 \|
	\| clip_fraction \| 0.0253 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.24 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.1e+05 \|
	\| n_updates \| 410 \|
	\| policy_gradient_loss \| -0.0026 \|
	\| std \| 0.894 \|
	\| value_loss \| 2.2e+05 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.67e+04 \|
	\| time/ \| \|
	\| fps \| 152 \|
	\| iterations \| 43 \|
	\| time_elapsed \| 577 \|
	\| total_timesteps \| 88064 \|
	\| train/ \| \|
	\| approx_kl \| 0.0030657728 \|
	\| clip_fraction \| 0.0121 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.22 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.52e+05 \|
	\| n_updates \| 420 \|
	\| policy_gradient_loss \| -0.00173 \|
	\| std \| 0.892 \|
	\| value_loss \| 3.03e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.73e+04 \|
	\| time/ \| \|
	\| fps \| 153 \|
	\| iterations \| 44 \|
	\| time_elapsed \| 588 \|
	\| total_timesteps \| 90112 \|
	\| train/ \| \|
	\| approx_kl \| 0.0051104454 \|
	\| clip_fraction \| 0.0357 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.22 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.25e+04 \|
	\| n_updates \| 430 \|
	\| policy_gradient_loss \| -0.00201 \|
	\| std \| 0.893 \|
	\| value_loss \| 1.81e+05 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.8e+04 \|
	\| time/ \| \|
	\| fps \| 153 \|
	\| iterations \| 45 \|
	\| time_elapsed \| 600 \|
	\| total_timesteps \| 92160 \|
	\| train/ \| \|
	\| approx_kl \| 0.0051720007 \|
	\| clip_fraction \| 0.033 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.23 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 3.47e+05 \|
	\| n_updates \| 440 \|
	\| policy_gradient_loss \| -0.00428 \|
	\| std \| 0.896 \|
	\| value_loss \| 7.59e+05 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.9e+04 \|
	\| time/ \| \|
	\| fps \| 153 \|
	\| iterations \| 46 \|
	\| time_elapsed \| 612 \|
	\| total_timesteps \| 94208 \|
	\| train/ \| \|
	\| approx_kl \| 0.004487371 \|
	\| clip_fraction \| 0.0192 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.23 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 6.84e+05 \|
	\| n_updates \| 450 \|
	\| policy_gradient_loss \| -0.00245 \|
	\| std \| 0.895 \|
	\| value_loss \| 1.3e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -2.98e+04 \|
	\| time/ \| \|
	\| fps \| 153 \|
	\| iterations \| 47 \|
	\| time_elapsed \| 625 \|
	\| total_timesteps \| 96256 \|
	\| train/ \| \|
	\| approx_kl \| 0.005325151 \|
	\| clip_fraction \| 0.0271 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.22 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 9.17e+05 \|
	\| n_updates \| 460 \|
	\| policy_gradient_loss \| -0.00341 \|
	\| std \| 0.892 \|
	\| value_loss \| 1.81e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.08e+04 \|
	\| time/ \| \|
	\| fps \| 154 \|
	\| iterations \| 48 \|
	\| time_elapsed \| 637 \|
	\| total_timesteps \| 98304 \|
	\| train/ \| \|
	\| approx_kl \| 0.004731435 \|
	\| clip_fraction \| 0.0245 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.21 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.34e+05 \|
	\| n_updates \| 470 \|
	\| policy_gradient_loss \| -0.00319 \|
	\| std \| 0.888 \|
	\| value_loss \| 1.53e+06 \|
	-----------------------------------------
	----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.21e+04 \|
	\| time/ \| \|
	\| fps \| 154 \|
	\| iterations \| 49 \|
	\| time_elapsed \| 648 \|
	\| total_timesteps \| 100352 \|
	\| train/ \| \|
	\| approx_kl \| 0.00386829 \|
	\| clip_fraction \| 0.00859 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.05e+06 \|
	\| n_updates \| 480 \|
	\| policy_gradient_loss \| -0.00151 \|
	\| std \| 0.887 \|
	\| value_loss \| 2.04e+06 \|
	----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.34e+04 \|
	\| time/ \| \|
	\| fps \| 154 \|
	\| iterations \| 50 \|
	\| time_elapsed \| 660 \|
	\| total_timesteps \| 102400 \|
	\| train/ \| \|
	\| approx_kl \| 0.005242249 \|
	\| clip_fraction \| 0.0372 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.95e+06 \|
	\| n_updates \| 490 \|
	\| policy_gradient_loss \| -0.00506 \|
	\| std \| 0.889 \|
	\| value_loss \| 3.17e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.5e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 51 \|
	\| time_elapsed \| 673 \|
	\| total_timesteps \| 104448 \|
	\| train/ \| \|
	\| approx_kl \| 0.003204999 \|
	\| clip_fraction \| 0.00566 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.21 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.29e+06 \|
	\| n_updates \| 500 \|
	\| policy_gradient_loss \| -0.000996 \|
	\| std \| 0.89 \|
	\| value_loss \| 3.12e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.71e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 52 \|
	\| time_elapsed \| 685 \|
	\| total_timesteps \| 106496 \|
	\| train/ \| \|
	\| approx_kl \| 0.0037713286 \|
	\| clip_fraction \| 0.0106 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.73e+06 \|
	\| n_updates \| 510 \|
	\| policy_gradient_loss \| -0.00205 \|
	\| std \| 0.889 \|
	\| value_loss \| 3.39e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -3.89e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 53 \|
	\| time_elapsed \| 699 \|
	\| total_timesteps \| 108544 \|
	\| train/ \| \|
	\| approx_kl \| 0.003621605 \|
	\| clip_fraction \| 0.00576 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.11e+06 \|
	\| n_updates \| 520 \|
	\| policy_gradient_loss \| -0.00108 \|
	\| std \| 0.889 \|
	\| value_loss \| 5.23e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.07e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 54 \|
	\| time_elapsed \| 710 \|
	\| total_timesteps \| 110592 \|
	\| train/ \| \|
	\| approx_kl \| 0.0037987605 \|
	\| clip_fraction \| 0.0108 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.21 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.02e+06 \|
	\| n_updates \| 530 \|
	\| policy_gradient_loss \| -0.00193 \|
	\| std \| 0.891 \|
	\| value_loss \| 4.78e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.31e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 55 \|
	\| time_elapsed \| 722 \|
	\| total_timesteps \| 112640 \|
	\| train/ \| \|
	\| approx_kl \| 0.0041659893 \|
	\| clip_fraction \| 0.00801 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.21 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.27e+06 \|
	\| n_updates \| 540 \|
	\| policy_gradient_loss \| -0.00111 \|
	\| std \| 0.89 \|
	\| value_loss \| 5e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.52e+04 \|
	\| time/ \| \|
	\| fps \| 156 \|
	\| iterations \| 56 \|
	\| time_elapsed \| 734 \|
	\| total_timesteps \| 114688 \|
	\| train/ \| \|
	\| approx_kl \| 0.0052787326 \|
	\| clip_fraction \| 0.0296 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.21 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 3.7e+06 \|
	\| n_updates \| 550 \|
	\| policy_gradient_loss \| -0.00406 \|
	\| std \| 0.889 \|
	\| value_loss \| 6.79e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.67e+04 \|
	\| time/ \| \|
	\| fps \| 156 \|
	\| iterations \| 57 \|
	\| time_elapsed \| 746 \|
	\| total_timesteps \| 116736 \|
	\| train/ \| \|
	\| approx_kl \| 0.004433933 \|
	\| clip_fraction \| 0.0184 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.93e+06 \|
	\| n_updates \| 560 \|
	\| policy_gradient_loss \| -0.00222 \|
	\| std \| 0.888 \|
	\| value_loss \| 6.15e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.83e+04 \|
	\| time/ \| \|
	\| fps \| 156 \|
	\| iterations \| 58 \|
	\| time_elapsed \| 758 \|
	\| total_timesteps \| 118784 \|
	\| train/ \| \|
	\| approx_kl \| 0.004643922 \|
	\| clip_fraction \| 0.025 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.54e+06 \|
	\| n_updates \| 570 \|
	\| policy_gradient_loss \| -0.00334 \|
	\| std \| 0.888 \|
	\| value_loss \| 4.8e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -4.99e+04 \|
	\| time/ \| \|
	\| fps \| 156 \|
	\| iterations \| 59 \|
	\| time_elapsed \| 769 \|
	\| total_timesteps \| 120832 \|
	\| train/ \| \|
	\| approx_kl \| 0.004279623 \|
	\| clip_fraction \| 0.00815 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.58e+06 \|
	\| n_updates \| 580 \|
	\| policy_gradient_loss \| -0.00133 \|
	\| std \| 0.89 \|
	\| value_loss \| 4.7e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -5.18e+04 \|
	\| time/ \| \|
	\| fps \| 157 \|
	\| iterations \| 60 \|
	\| time_elapsed \| 782 \|
	\| total_timesteps \| 122880 \|
	\| train/ \| \|
	\| approx_kl \| 0.004928913 \|
	\| clip_fraction \| 0.0252 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.06e+06 \|
	\| n_updates \| 590 \|
	\| policy_gradient_loss \| -0.00314 \|
	\| std \| 0.886 \|
	\| value_loss \| 4.64e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -5.37e+04 \|
	\| time/ \| \|
	\| fps \| 157 \|
	\| iterations \| 61 \|
	\| time_elapsed \| 793 \|
	\| total_timesteps \| 124928 \|
	\| train/ \| \|
	\| approx_kl \| 0.0044577485 \|
	\| clip_fraction \| 0.0167 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.19 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.75e+06 \|
	\| n_updates \| 600 \|
	\| policy_gradient_loss \| -0.00216 \|
	\| std \| 0.884 \|
	\| value_loss \| 5.37e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -5.54e+04 \|
	\| time/ \| \|
	\| fps \| 157 \|
	\| iterations \| 62 \|
	\| time_elapsed \| 805 \|
	\| total_timesteps \| 126976 \|
	\| train/ \| \|
	\| approx_kl \| 0.0033779903 \|
	\| clip_fraction \| 0.00854 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.19 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.75e+06 \|
	\| n_updates \| 610 \|
	\| policy_gradient_loss \| -0.000881 \|
	\| std \| 0.887 \|
	\| value_loss \| 5.11e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -5.84e+04 \|
	\| time/ \| \|
	\| fps \| 157 \|
	\| iterations \| 63 \|
	\| time_elapsed \| 817 \|
	\| total_timesteps \| 129024 \|
	\| train/ \| \|
	\| approx_kl \| 0.0036522774 \|
	\| clip_fraction \| 0.00669 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.36e+06 \|
	\| n_updates \| 620 \|
	\| policy_gradient_loss \| -0.00121 \|
	\| std \| 0.889 \|
	\| value_loss \| 5.49e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.02e+04 \|
	\| time/ \| \|
	\| fps \| 158 \|
	\| iterations \| 64 \|
	\| time_elapsed \| 829 \|
	\| total_timesteps \| 131072 \|
	\| train/ \| \|
	\| approx_kl \| 0.005089692 \|
	\| clip_fraction \| 0.0314 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.64e+06 \|
	\| n_updates \| 630 \|
	\| policy_gradient_loss \| -0.00405 \|
	\| std \| 0.887 \|
	\| value_loss \| 5.26e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.17e+04 \|
	\| time/ \| \|
	\| fps \| 158 \|
	\| iterations \| 65 \|
	\| time_elapsed \| 841 \|
	\| total_timesteps \| 133120 \|
	\| train/ \| \|
	\| approx_kl \| 0.004889611 \|
	\| clip_fraction \| 0.0176 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.2 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.92e+06 \|
	\| n_updates \| 640 \|
	\| policy_gradient_loss \| -0.00247 \|
	\| std \| 0.888 \|
	\| value_loss \| 4.65e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.28e+04 \|
	\| time/ \| \|
	\| fps \| 158 \|
	\| iterations \| 66 \|
	\| time_elapsed \| 853 \|
	\| total_timesteps \| 135168 \|
	\| train/ \| \|
	\| approx_kl \| 0.004658374 \|
	\| clip_fraction \| 0.021 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.19 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.67e+06 \|
	\| n_updates \| 650 \|
	\| policy_gradient_loss \| -0.00222 \|
	\| std \| 0.886 \|
	\| value_loss \| 3.85e+06 \|
	-----------------------------------------
	----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.38e+04 \|
	\| time/ \| \|
	\| fps \| 158 \|
	\| iterations \| 67 \|
	\| time_elapsed \| 866 \|
	\| total_timesteps \| 137216 \|
	\| train/ \| \|
	\| approx_kl \| 0.00569404 \|
	\| clip_fraction \| 0.0394 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.19 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.44e+06 \|
	\| n_updates \| 660 \|
	\| policy_gradient_loss \| -0.00414 \|
	\| std \| 0.887 \|
	\| value_loss \| 2.78e+06 \|
	----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.47e+04 \|
	\| time/ \| \|
	\| fps \| 157 \|
	\| iterations \| 68 \|
	\| time_elapsed \| 887 \|
	\| total_timesteps \| 139264 \|
	\| train/ \| \|
	\| approx_kl \| 0.004979359 \|
	\| clip_fraction \| 0.0314 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.19 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 7.57e+05 \|
	\| n_updates \| 670 \|
	\| policy_gradient_loss \| -0.00347 \|
	\| std \| 0.883 \|
	\| value_loss \| 1.69e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.6e+04 \|
	\| time/ \| \|
	\| fps \| 155 \|
	\| iterations \| 69 \|
	\| time_elapsed \| 911 \|
	\| total_timesteps \| 141312 \|
	\| train/ \| \|
	\| approx_kl \| 0.003934146 \|
	\| clip_fraction \| 0.0181 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.17 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.59e+05 \|
	\| n_updates \| 680 \|
	\| policy_gradient_loss \| -0.002 \|
	\| std \| 0.882 \|
	\| value_loss \| 1.66e+06 \|
	-----------------------------------------
	----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.73e+04 \|
	\| time/ \| \|
	\| fps \| 154 \|
	\| iterations \| 70 \|
	\| time_elapsed \| 929 \|
	\| total_timesteps \| 143360 \|
	\| train/ \| \|
	\| approx_kl \| 0.00488944 \|
	\| clip_fraction \| 0.0386 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.17 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.07e+06 \|
	\| n_updates \| 690 \|
	\| policy_gradient_loss \| -0.00419 \|
	\| std \| 0.879 \|
	\| value_loss \| 2.26e+06 \|
	----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -6.88e+04 \|
	\| time/ \| \|
	\| fps \| 151 \|
	\| iterations \| 71 \|
	\| time_elapsed \| 956 \|
	\| total_timesteps \| 145408 \|
	\| train/ \| \|
	\| approx_kl \| 0.0039507896 \|
	\| clip_fraction \| 0.026 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.16 \|
	\| explained_variance \| -2.38e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.23e+06 \|
	\| n_updates \| 700 \|
	\| policy_gradient_loss \| -0.00263 \|
	\| std \| 0.879 \|
	\| value_loss \| 2.33e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7e+04 \|
	\| time/ \| \|
	\| fps \| 151 \|
	\| iterations \| 72 \|
	\| time_elapsed \| 974 \|
	\| total_timesteps \| 147456 \|
	\| train/ \| \|
	\| approx_kl \| 0.0048819017 \|
	\| clip_fraction \| 0.0321 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.16 \|
	\| explained_variance \| -1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.66e+06 \|
	\| n_updates \| 710 \|
	\| policy_gradient_loss \| -0.00324 \|
	\| std \| 0.877 \|
	\| value_loss \| 3.4e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.08e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 73 \|
	\| time_elapsed \| 994 \|
	\| total_timesteps \| 149504 \|
	\| train/ \| \|
	\| approx_kl \| 0.0051534167 \|
	\| clip_fraction \| 0.0276 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.15 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.15e+06 \|
	\| n_updates \| 720 \|
	\| policy_gradient_loss \| -0.0034 \|
	\| std \| 0.877 \|
	\| value_loss \| 2.73e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.17e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 74 \|
	\| time_elapsed \| 1009 \|
	\| total_timesteps \| 151552 \|
	\| train/ \| \|
	\| approx_kl \| 0.0039522136 \|
	\| clip_fraction \| 0.0215 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.17 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.39e+05 \|
	\| n_updates \| 730 \|
	\| policy_gradient_loss \| -0.00278 \|
	\| std \| 0.885 \|
	\| value_loss \| 1.82e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.25e+04 \|
	\| time/ \| \|
	\| fps \| 150 \|
	\| iterations \| 75 \|
	\| time_elapsed \| 1023 \|
	\| total_timesteps \| 153600 \|
	\| train/ \| \|
	\| approx_kl \| 0.0037896927 \|
	\| clip_fraction \| 0.0131 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.18 \|
	\| explained_variance \| 1.19e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.18e+06 \|
	\| n_updates \| 740 \|
	\| policy_gradient_loss \| -0.00183 \|
	\| std \| 0.883 \|
	\| value_loss \| 2.15e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.33e+04 \|
	\| time/ \| \|
	\| fps \| 149 \|
	\| iterations \| 76 \|
	\| time_elapsed \| 1038 \|
	\| total_timesteps \| 155648 \|
	\| train/ \| \|
	\| approx_kl \| 0.005035511 \|
	\| clip_fraction \| 0.0261 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.16 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 6.91e+05 \|
	\| n_updates \| 750 \|
	\| policy_gradient_loss \| -0.00347 \|
	\| std \| 0.877 \|
	\| value_loss \| 1.49e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.45e+04 \|
	\| time/ \| \|
	\| fps \| 149 \|
	\| iterations \| 77 \|
	\| time_elapsed \| 1052 \|
	\| total_timesteps \| 157696 \|
	\| train/ \| \|
	\| approx_kl \| 0.005323178 \|
	\| clip_fraction \| 0.0373 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.15 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 8.95e+05 \|
	\| n_updates \| 760 \|
	\| policy_gradient_loss \| -0.00419 \|
	\| std \| 0.876 \|
	\| value_loss \| 1.9e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.61e+04 \|
	\| time/ \| \|
	\| fps \| 149 \|
	\| iterations \| 78 \|
	\| time_elapsed \| 1071 \|
	\| total_timesteps \| 159744 \|
	\| train/ \| \|
	\| approx_kl \| 0.005339088 \|
	\| clip_fraction \| 0.0279 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.56e+06 \|
	\| n_updates \| 770 \|
	\| policy_gradient_loss \| -0.00348 \|
	\| std \| 0.871 \|
	\| value_loss \| 3.12e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.72e+04 \|
	\| time/ \| \|
	\| fps \| 148 \|
	\| iterations \| 79 \|
	\| time_elapsed \| 1088 \|
	\| total_timesteps \| 161792 \|
	\| train/ \| \|
	\| approx_kl \| 0.0021434259 \|
	\| clip_fraction \| 0.00132 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.39e+06 \|
	\| n_updates \| 780 \|
	\| policy_gradient_loss \| -0.000295 \|
	\| std \| 0.874 \|
	\| value_loss \| 3.14e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -7.88e+04 \|
	\| time/ \| \|
	\| fps \| 148 \|
	\| iterations \| 80 \|
	\| time_elapsed \| 1106 \|
	\| total_timesteps \| 163840 \|
	\| train/ \| \|
	\| approx_kl \| 0.004515986 \|
	\| clip_fraction \| 0.0185 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| -2.38e-07 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.26e+06 \|
	\| n_updates \| 790 \|
	\| policy_gradient_loss \| -0.00181 \|
	\| std \| 0.872 \|
	\| value_loss \| 2.6e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.02e+04 \|
	\| time/ \| \|
	\| fps \| 147 \|
	\| iterations \| 81 \|
	\| time_elapsed \| 1125 \|
	\| total_timesteps \| 165888 \|
	\| train/ \| \|
	\| approx_kl \| 0.004079287 \|
	\| clip_fraction \| 0.0139 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 5.96e-08 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.86e+06 \|
	\| n_updates \| 800 \|
	\| policy_gradient_loss \| -0.00189 \|
	\| std \| 0.873 \|
	\| value_loss \| 3.26e+06 \|
	-----------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.2e+04 \|
	\| time/ \| \|
	\| fps \| 146 \|
	\| iterations \| 82 \|
	\| time_elapsed \| 1147 \|
	\| total_timesteps \| 167936 \|
	\| train/ \| \|
	\| approx_kl \| 0.004386483 \|
	\| clip_fraction \| 0.0127 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.87e+06 \|
	\| n_updates \| 810 \|
	\| policy_gradient_loss \| -0.00205 \|
	\| std \| 0.873 \|
	\| value_loss \| 3.56e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.37e+04 \|
	\| time/ \| \|
	\| fps \| 145 \|
	\| iterations \| 83 \|
	\| time_elapsed \| 1167 \|
	\| total_timesteps \| 169984 \|
	\| train/ \| \|
	\| approx_kl \| 0.0041227336 \|
	\| clip_fraction \| 0.0245 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.14 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.95e+06 \|
	\| n_updates \| 820 \|
	\| policy_gradient_loss \| -0.00324 \|
	\| std \| 0.873 \|
	\| value_loss \| 3.58e+06 \|
	------------------------------------------
	----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.62e+04 \|
	\| time/ \| \|
	\| fps \| 145 \|
	\| iterations \| 84 \|
	\| time_elapsed \| 1180 \|
	\| total_timesteps \| 172032 \|
	\| train/ \| \|
	\| approx_kl \| 0.00430945 \|
	\| clip_fraction \| 0.0171 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.18e+06 \|
	\| n_updates \| 830 \|
	\| policy_gradient_loss \| -0.0021 \|
	\| std \| 0.872 \|
	\| value_loss \| 3.97e+06 \|
	----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.81e+04 \|
	\| time/ \| \|
	\| fps \| 145 \|
	\| iterations \| 85 \|
	\| time_elapsed \| 1198 \|
	\| total_timesteps \| 174080 \|
	\| train/ \| \|
	\| approx_kl \| 0.0027071913 \|
	\| clip_fraction \| 0.0043 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.14 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.6e+06 \|
	\| n_updates \| 840 \|
	\| policy_gradient_loss \| -0.000301 \|
	\| std \| 0.876 \|
	\| value_loss \| 3.94e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -8.97e+04 \|
	\| time/ \| \|
	\| fps \| 144 \|
	\| iterations \| 86 \|
	\| time_elapsed \| 1218 \|
	\| total_timesteps \| 176128 \|
	\| train/ \| \|
	\| approx_kl \| 0.003243664 \|
	\| clip_fraction \| 0.0133 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.15 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.15e+06 \|
	\| n_updates \| 850 \|
	\| policy_gradient_loss \| -0.00204 \|
	\| std \| 0.878 \|
	\| value_loss \| 4.5e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -9.15e+04 \|
	\| time/ \| \|
	\| fps \| 143 \|
	\| iterations \| 87 \|
	\| time_elapsed \| 1239 \|
	\| total_timesteps \| 178176 \|
	\| train/ \| \|
	\| approx_kl \| 0.0029459428 \|
	\| clip_fraction \| 0.00308 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.16 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.44e+06 \|
	\| n_updates \| 860 \|
	\| policy_gradient_loss \| -0.000751 \|
	\| std \| 0.88 \|
	\| value_loss \| 4.24e+06 \|
	------------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -9.36e+04 \|
	\| time/ \| \|
	\| fps \| 143 \|
	\| iterations \| 88 \|
	\| time_elapsed \| 1258 \|
	\| total_timesteps \| 180224 \|
	\| train/ \| \|
	\| approx_kl \| 0.0043680565 \|
	\| clip_fraction \| 0.0208 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.17 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.09e+06 \|
	\| n_updates \| 870 \|
	\| policy_gradient_loss \| -0.00237 \|
	\| std \| 0.881 \|
	\| value_loss \| 4.39e+06 \|
	------------------------------------------
	-----------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -9.52e+04 \|
	\| time/ \| \|
	\| fps \| 142 \|
	\| iterations \| 89 \|
	\| time_elapsed \| 1283 \|
	\| total_timesteps \| 182272 \|
	\| train/ \| \|
	\| approx_kl \| 0.004063189 \|
	\| clip_fraction \| 0.012 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.16 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 2.77e+06 \|
	\| n_updates \| 880 \|
	\| policy_gradient_loss \| -0.00207 \|
	\| std \| 0.877 \|
	\| value_loss \| 4.73e+06 \|
	-----------------------------------------
	------------------------------------------
	\| rollout/ \| \|
	\| ep_len_mean \| 1e+03 \|
	\| ep_rew_mean \| -9.69e+04 \|
	\| time/ \| \|
	\| fps \| 141 \|
	\| iterations \| 90 \|
	\| time_elapsed \| 1306 \|
	\| total_timesteps \| 184320 \|
	\| train/ \| \|
	\| approx_kl \| 0.0049707354 \|
	\| clip_fraction \| 0.0279 \|
	\| clip_range \| 0.2 \|
	\| entropy_loss \| -5.13 \|
	\| explained_variance \| 0 \|
	\| learning_rate \| 0.0003 \|
	\| loss \| 1.65e+06 \|
	\| n_updates \| 890 \|
	\| policy_gradient_loss \| -0.00372 \|
	\| std \| 0.871 \|
	\| value_loss \| 3.68e+06 \|
	------------------------------------------