{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9801653623580933, "min": 0.9801653623580933, "max": 1.4905848503112793, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 29593.15234375, "min": 29593.15234375, "max": 45218.3828125, "count": 3 }, "Pyramids.Step.mean": { "value": 89991.0, "min": 29952.0, "max": 89991.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89991.0, "min": 29952.0, "max": 89991.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08172116428613663, "min": -0.18514548242092133, "max": -0.08172116428613663, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.85824203491211, "min": -43.879478454589844, "max": -19.85824203491211, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17595750093460083, "min": 0.17595750093460083, "max": 0.30657637119293213, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 42.75767135620117, "min": 42.75767135620117, "max": 73.88490295410156, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06912930754630443, "min": 0.06912930754630443, "max": 0.07201134016691368, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7604223830093487, "min": 0.5040793811683958, "max": 0.7604223830093487, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0030500191075133755, "min": 0.0015892533351976538, "max": 0.005062415475298746, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03355021018264713, "min": 0.01271402668158123, "max": 0.035436908327091225, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.359307546899998e-05, "min": 7.359307546899998e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0008095238301589998, "min": 0.0008095238301589998, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12453099999999999, "min": 0.12453099999999999, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3698409999999999, "min": 1.232864, "max": 1.3698409999999999, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0024606469000000002, "min": 0.0024606469000000002, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0270671159, "min": 0.0270671159, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10749976336956024, "min": 0.10749976336956024, "max": 0.4734865128993988, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.1824973821640015, "min": 1.1824973821640015, "max": 3.314405679702759, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 930.8571428571429, "min": 930.8571428571429, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32580.0, "min": 15984.0, "max": 32639.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.6459714693682534, "min": -1.0000000521540642, "max": -0.6459714693682534, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -22.60900142788887, "min": -30.671001717448235, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.6459714693682534, "min": -1.0000000521540642, "max": -0.6459714693682534, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -22.60900142788887, "min": -30.671001717448235, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1526742964982986, "min": 1.1526742964982986, "max": 9.67969429679215, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 40.34360037744045, "min": 40.34360037744045, "max": 154.8751087486744, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1755013700", "python_version": "3.10.12 (main, Aug 12 2025, 16:39:32) [GCC 12.2.0]", "command_line_arguments": "/home/tehrani/.pyenv/versions/3.10.12/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1755013760" }, "total": 60.509338764473796, "count": 1, "self": 0.220870696939528, "children": { "run_training.setup": { "total": 0.01870640367269516, "count": 1, "self": 0.01870640367269516 }, "TrainerController.start_learning": { "total": 60.26976166386157, "count": 1, "self": 0.051000011153519154, "children": { "TrainerController._reset_env": { "total": 2.343051176518202, "count": 1, "self": 2.343051176518202 }, "TrainerController.advance": { "total": 57.490975469350815, "count": 6336, "self": 0.05026277061551809, "children": { "env_step": { "total": 32.86948547232896, "count": 6336, "self": 28.169951912947, "children": { "SubprocessEnvManager._take_step": { "total": 4.666951126419008, "count": 6336, "self": 0.1808412317186594, "children": { "TorchPolicy.evaluate": { "total": 4.486109894700348, "count": 6326, "self": 4.486109894700348 } } }, "workers": { "total": 0.032582432962954044, "count": 6336, "self": 0.0, "children": { "worker_root": { "total": 59.83198019582778, "count": 6336, "is_parallel": true, "self": 35.113404024392366, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006738267838954926, "count": 1, "is_parallel": true, "self": 0.00018783006817102432, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048599671572446823, "count": 8, "is_parallel": true, "self": 0.00048599671572446823 } } }, "UnityEnvironment.step": { "total": 0.013978883624076843, "count": 1, "is_parallel": true, "self": 0.00014815013855695724, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001464691013097763, "count": 1, "is_parallel": true, "self": 0.0001464691013097763 }, "communicator.exchange": { "total": 0.013263914734125137, "count": 1, "is_parallel": true, "self": 0.013263914734125137 }, "steps_from_proto": { "total": 0.0004203496500849724, "count": 1, "is_parallel": true, "self": 9.6101313829422e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003242483362555504, "count": 8, "is_parallel": true, "self": 0.0003242483362555504 } } } } } } }, "UnityEnvironment.step": { "total": 24.718576171435416, "count": 6335, "is_parallel": true, "self": 0.7724612429738045, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5127775631844997, "count": 6335, "is_parallel": true, "self": 0.5127775631844997 }, "communicator.exchange": { "total": 21.159241074696183, "count": 6335, "is_parallel": true, "self": 21.159241074696183 }, "steps_from_proto": { "total": 2.2740962905809283, "count": 6335, "is_parallel": true, "self": 0.4757897472009063, "children": { "_process_rank_one_or_two_observation": { "total": 1.798306543380022, "count": 50680, "is_parallel": true, "self": 1.798306543380022 } } } } } } } } } } }, "trainer_advance": { "total": 24.571227226406336, "count": 6336, "self": 0.06450209114700556, "children": { "process_trajectory": { "total": 4.351756627671421, "count": 6336, "self": 4.351756627671421 }, "_update_policy": { "total": 20.15496850758791, "count": 30, "self": 12.527653916738927, "children": { "TorchPPOOptimizer.update": { "total": 7.627314590848982, "count": 2289, "self": 7.627314590848982 } } } } } } }, "trainer_threads": { "total": 4.908069968223572e-07, "count": 1, "self": 4.908069968223572e-07 }, "TrainerController._save_models": { "total": 0.3847345160320401, "count": 1, "self": 0.017062720842659473, "children": { "RLTrainer._checkpoint": { "total": 0.36767179518938065, "count": 1, "self": 0.36767179518938065 } } } } } } }