{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25000306963920593, "min": 0.23880161345005035, "max": 1.455433964729309, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7428.0908203125, "min": 7194.615234375, "max": 44152.04296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989876.0, "min": 29916.0, "max": 989876.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989876.0, "min": 29916.0, "max": 989876.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6816778779029846, "min": -0.10856284201145172, "max": 0.7192277312278748, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.32322692871094, "min": -25.729393005371094, "max": 209.29527282714844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02241593971848488, "min": 0.006272487808018923, "max": 0.3675876259803772, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.4557905197143555, "min": 1.699844241142273, "max": 87.22477722167969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06993540977740906, "min": 0.06604293696582318, "max": 0.07458009163376225, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9790957368837269, "min": 0.5220606414363358, "max": 1.0269671495497117, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01651150790584164, "min": 0.002355096557827654, "max": 0.01727149668015952, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23116111068178297, "min": 0.03297135180958716, "max": 0.24192296081067372, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.518976065135718e-06, "min": 7.518976065135718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010526566491190005, "min": 0.00010526566491190005, "max": 0.0037573729475423997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250629285714287, "min": 0.10250629285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350881000000002, "min": 1.3886848, "max": 2.6524576, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603786564285715, "min": 0.0002603786564285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003645301190000001, "min": 0.003645301190000001, "max": 0.12526051424, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014971639029681683, "min": 0.014971639029681683, "max": 0.5749228596687317, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.209602952003479, "min": 0.209602952003479, "max": 4.0244598388671875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 269.33962264150944, "min": 262.7241379310345, "max": 990.7647058823529, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28550.0, "min": 16843.0, "max": 32348.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7306603592521739, "min": -0.874058872461319, "max": 1.7306603592521739, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 183.44999808073044, "min": -28.195201590657234, "max": 193.5211983397603, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7306603592521739, "min": -0.874058872461319, "max": 1.7306603592521739, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 183.44999808073044, "min": -28.195201590657234, "max": 193.5211983397603, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04188961147595381, "min": 0.04188961147595381, "max": 11.54839026226717, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.440298816451104, "min": 4.440298816451104, "max": 196.32263445854187, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728369759", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728372101" }, "total": 2342.740032271, "count": 1, "self": 1.200523824999891, "children": { "run_training.setup": { "total": 0.05588389900003676, "count": 1, "self": 0.05588389900003676 }, "TrainerController.start_learning": { "total": 2341.483624547, "count": 1, "self": 1.4195460429646118, "children": { "TrainerController._reset_env": { "total": 1.692349633000049, "count": 1, "self": 1.692349633000049 }, "TrainerController.advance": { "total": 2338.269921287036, "count": 64403, "self": 1.4309861959904993, "children": { "env_step": { "total": 1661.0976458139885, "count": 64403, "self": 1503.118092326998, "children": { "SubprocessEnvManager._take_step": { "total": 157.1125626250382, "count": 64403, "self": 5.008834594034852, "children": { "TorchPolicy.evaluate": { "total": 152.10372803100336, "count": 62571, "self": 152.10372803100336 } } }, "workers": { "total": 0.8669908619522175, "count": 64403, "self": 0.0, "children": { "worker_root": { "total": 2336.4868390660154, "count": 64403, "is_parallel": true, "self": 956.402758070079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021710500000153843, "count": 1, "is_parallel": true, "self": 0.0007266659999913827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014443840000240016, "count": 8, "is_parallel": true, "self": 0.0014443840000240016 } } }, "UnityEnvironment.step": { "total": 0.04890347700006714, "count": 1, "is_parallel": true, "self": 0.000638063999986116, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004837419999148551, "count": 1, "is_parallel": true, "self": 0.0004837419999148551 }, "communicator.exchange": { "total": 0.04605444800017722, "count": 1, "is_parallel": true, "self": 0.04605444800017722 }, "steps_from_proto": { "total": 0.0017272229999889532, "count": 1, "is_parallel": true, "self": 0.0003792859999975917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013479369999913615, "count": 8, "is_parallel": true, "self": 0.0013479369999913615 } } } } } } }, "UnityEnvironment.step": { "total": 1380.0840809959363, "count": 64402, "is_parallel": true, "self": 34.06382499382016, "children": { "UnityEnvironment._generate_step_input": { "total": 23.200935926030525, "count": 64402, "is_parallel": true, "self": 23.200935926030525 }, "communicator.exchange": { "total": 1222.8361003689654, "count": 64402, "is_parallel": true, "self": 1222.8361003689654 }, "steps_from_proto": { "total": 99.98321970712027, "count": 64402, "is_parallel": true, "self": 20.965705947191964, "children": { "_process_rank_one_or_two_observation": { "total": 79.0175137599283, "count": 515216, "is_parallel": true, "self": 79.0175137599283 } } } } } } } } } } }, "trainer_advance": { "total": 675.7412892770571, "count": 64403, "self": 2.7944835800435612, "children": { "process_trajectory": { "total": 134.4746958970136, "count": 64403, "self": 134.219979738014, "children": { "RLTrainer._checkpoint": { "total": 0.25471615899959943, "count": 2, "self": 0.25471615899959943 } } }, "_update_policy": { "total": 538.4721098, "count": 458, "self": 302.39412571903654, "children": { "TorchPPOOptimizer.update": { "total": 236.07798408096346, "count": 22803, "self": 236.07798408096346 } } } } } } }, "trainer_threads": { "total": 1.0669996299839113e-06, "count": 1, "self": 1.0669996299839113e-06 }, "TrainerController._save_models": { "total": 0.10180651699965892, "count": 1, "self": 0.002064781999706611, "children": { "RLTrainer._checkpoint": { "total": 0.09974173499995231, "count": 1, "self": 0.09974173499995231 } } } } } } }