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 | -1.79e+04 | | time/ | | | fps | 465 | | iterations | 1 | | time_elapsed | 4 | | total_timesteps | 2048 | ---------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -1.91e+04 | | time/ | | | fps | 24 | | iterations | 2 | | time_elapsed | 169 | | total_timesteps | 4096 | | train/ | | | approx_kl | 0.004881427 | | clip_fraction | 0.0184 | | clip_range | 0.2 | | entropy_loss | -5.67 | | explained_variance | 0.000221 | | learning_rate | 0.0003 | | loss | 4.46e+04 | | n_updates | 10 | | policy_gradient_loss | -0.00155 | | std | 0.998 | | value_loss | 9.86e+04 | ----------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.01e+04 | | time/ | | | fps | 31 | | iterations | 3 | | time_elapsed | 196 | | total_timesteps | 6144 | | train/ | | | approx_kl | 0.0020806824 | | clip_fraction | 0.00215 | | clip_range | 0.2 | | entropy_loss | -5.66 | | explained_variance | -6.6e-05 | | learning_rate | 0.0003 | | loss | 6.96e+04 | | n_updates | 20 | | policy_gradient_loss | -0.000315 | | std | 0.996 | | value_loss | 1.37e+05 | ------------------------------------------ ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.08e+04 | | time/ | | | fps | 36 | | iterations | 4 | | time_elapsed | 226 | | total_timesteps | 8192 | | train/ | | | approx_kl | 0.0041169263 | | clip_fraction | 0.0206 | | clip_range | 0.2 | | entropy_loss | -5.66 | | explained_variance | -5.96e-06 | | learning_rate | 0.0003 | | loss | 7.12e+04 | | n_updates | 30 | | policy_gradient_loss | -0.00234 | | std | 0.994 | | value_loss | 1.63e+05 | ------------------------------------------ ----------------------------------------- | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.1e+04 | | time/ | | | fps | 42 | | iterations | 5 | | time_elapsed | 242 | | total_timesteps | 10240 | | train/ | | | approx_kl | 0.003560378 | | clip_fraction | 0.0138 | | clip_range | 0.2 | | entropy_loss | -5.66 | | explained_variance | 6.62e-06 | | learning_rate | 0.0003 | | loss | 8.45e+04 | | n_updates | 40 | | policy_gradient_loss | -0.00122 | | std | 0.998 | | value_loss | 1.94e+05 | ----------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.13e+04 | | time/ | | | fps | 47 | | iterations | 6 | | time_elapsed | 258 | | total_timesteps | 12288 | | train/ | | | approx_kl | 0.0027945049 | | clip_fraction | 0.0139 | | clip_range | 0.2 | | entropy_loss | -5.67 | | explained_variance | 2.8e-06 | | learning_rate | 0.0003 | | loss | 6.45e+04 | | n_updates | 50 | | policy_gradient_loss | -0.00151 | | std | 1 | | value_loss | 1.47e+05 | ------------------------------------------ ----------------------------------------- | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.19e+04 | | time/ | | | fps | 52 | | iterations | 7 | | time_elapsed | 274 | | total_timesteps | 14336 | | train/ | | | approx_kl | 0.004093081 | | clip_fraction | 0.018 | | clip_range | 0.2 | | entropy_loss | -5.68 | | explained_variance | 1.79e-07 | | learning_rate | 0.0003 | | loss | 9.83e+04 | | n_updates | 60 | | policy_gradient_loss | -0.00117 | | std | 1 | | value_loss | 1.69e+05 | ----------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.21e+04 | | time/ | | | fps | 56 | | iterations | 8 | | time_elapsed | 290 | | total_timesteps | 16384 | | train/ | | | approx_kl | 0.0041737873 | | clip_fraction | 0.0396 | | clip_range | 0.2 | | entropy_loss | -5.67 | | explained_variance | -2.38e-07 | | learning_rate | 0.0003 | | loss | 9.31e+04 | | n_updates | 70 | | policy_gradient_loss | -0.00342 | | std | 0.996 | | value_loss | 1.76e+05 | ------------------------------------------ ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.21e+04 | | time/ | | | fps | 59 | | iterations | 9 | | time_elapsed | 309 | | total_timesteps | 18432 | | train/ | | | approx_kl | 0.0060277004 | | clip_fraction | 0.037 | | clip_range | 0.2 | | entropy_loss | -5.65 | | explained_variance | 2.21e-06 | | learning_rate | 0.0003 | | loss | 6.73e+04 | | n_updates | 80 | | policy_gradient_loss | -0.00309 | | std | 0.991 | | value_loss | 1.55e+05 | ------------------------------------------ ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.32e+04 | | time/ | | | fps | 62 | | iterations | 10 | | time_elapsed | 326 | | total_timesteps | 20480 | | train/ | | | approx_kl | 0.0032014307 | | clip_fraction | 0.0083 | | clip_range | 0.2 | | entropy_loss | -5.63 | | explained_variance | 2.98e-07 | | learning_rate | 0.0003 | | loss | 8.79e+04 | | n_updates | 90 | | policy_gradient_loss | -0.000593 | | std | 0.989 | | value_loss | 1.53e+05 | ------------------------------------------ ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.57e+04 | | time/ | | | fps | 64 | | iterations | 11 | | time_elapsed | 348 | | total_timesteps | 22528 | | train/ | | | approx_kl | 0.0035356751 | | clip_fraction | 0.012 | | clip_range | 0.2 | | entropy_loss | -5.61 | | explained_variance | 5.96e-08 | | learning_rate | 0.0003 | | loss | 1.91e+05 | | n_updates | 100 | | policy_gradient_loss | -0.00137 | | std | 0.981 | | value_loss | 3.78e+05 | ------------------------------------------ ------------------------------------------ | rollout/ | | | ep_len_mean | 1e+03 | | ep_rew_mean | -2.78e+04 | | time/ | | | fps | 67 | | iterations | 12 | | time_elapsed | 365 | | total_timesteps | 24576 | | train/ | | | approx_kl | 0.0027306664 | | clip_fraction | 0.00293 | | clip_range | 0.2 | | entropy_loss | -5.6 | | explained_variance | 1.79e-07 | | learning_rate | 0.0003 | | loss | 4.31e+05 | | n_updates | 110 | | policy_gradient_loss | -0.000544 | | std | 0.983 | | value_loss | 9.15e+05 | ------------------------------------------ Traceback (most recent call last): File "/home/ylop/Documents/drone go brr/Drone-go-brrrrr/Drone-go-brrrrr/train.py", line 35, in train() ~~~~~^^ File "/home/ylop/Documents/drone go brr/Drone-go-brrrrr/Drone-go-brrrrr/train.py", line 28, in train model.learn(total_timesteps=total_timesteps, callback=checkpoint_callback) ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/ppo/ppo.py", line 311, in learn return super().learn( ~~~~~~~~~~~~~^ total_timesteps=total_timesteps, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<4 lines>... progress_bar=progress_bar, ^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 324, in learn continue_training = self.collect_rollouts(self.env, callback, self.rollout_buffer, n_rollout_steps=self.n_steps) File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 202, in collect_rollouts actions, values, log_probs = self.policy(obs_tensor) ~~~~~~~~~~~^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl return forward_call(*args, **kwargs) File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/policies.py", line 645, in forward features = self.extract_features(obs) File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/policies.py", line 672, in extract_features return super().extract_features(obs, self.features_extractor if features_extractor is None else features_extractor) ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/stable_baselines3/common/policies.py", line 131, in extract_features return features_extractor(preprocessed_obs) File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl return forward_call(*args, **kwargs) File "/home/ylop/Documents/drone go brr/Drone-go-brrrrr/Drone-go-brrrrr/models/liquid_ppo.py", line 58, in forward output, self.hx = self.ltc(observations, self.hx) ~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl return forward_call(*args, **kwargs) File "/home/ylop/.local/lib/python3.14/site-packages/ncps/torch/ltc.py", line 185, in forward h_out, h_state = self.rnn_cell.forward(inputs, h_state, ts) ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^ File "/home/ylop/.local/lib/python3.14/site-packages/ncps/torch/ltc_cell.py", line 282, in forward next_state = self._ode_solver(inputs, states, elapsed_time) File "/home/ylop/.local/lib/python3.14/site-packages/ncps/torch/ltc_cell.py", line 247, in _ode_solver v_pre = numerator / (denominator + self._epsilon) ^^^^^ KeyboardInterrupt