{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.704181432723999, "min": 0.704181432723999, "max": 1.4420181512832642, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 21091.642578125, "min": 21091.642578125, "max": 43745.0625, "count": 10 }, "Pyramids.Step.mean": { "value": 299998.0, "min": 29939.0, "max": 299998.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299998.0, "min": 29939.0, "max": 299998.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06615421921014786, "min": -0.21818986535072327, "max": -0.03297995403409004, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.943167686462402, "min": -51.71099853515625, "max": -7.915188789367676, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03181059658527374, "min": 0.03181059658527374, "max": 0.4717663824558258, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.666354179382324, "min": 7.666354179382324, "max": 111.80863189697266, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06608748776559592, "min": 0.0650946730015156, "max": 0.07354978325885465, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9252248287183429, "min": 0.5059748568045893, "max": 0.9561471823651104, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0015892796493671452, "min": 0.000761867436767018, "max": 0.006258429338666095, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.02224991509114003, "min": 0.010666144114738253, "max": 0.04490969698789862, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.55198091124762e-05, "min": 1.55198091124762e-05, "max": 0.00028411157672471424, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002172773275746668, "min": 0.0002172773275746668, "max": 0.002819791160069666, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10517323809523811, "min": 0.10517323809523811, "max": 0.1947038571428572, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4724253333333335, "min": 1.3629270000000004, "max": 2.1693686666666667, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005268064857142861, "min": 0.0005268064857142861, "max": 0.009470915328571429, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.007375290800000005, "min": 0.007375290800000005, "max": 0.09400904030000001, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02906503714621067, "min": 0.02906503714621067, "max": 0.3680463135242462, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4069105088710785, "min": 0.4069105088710785, "max": 2.576324224472046, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 958.34375, "min": 899.7777777777778, "max": 990.7666666666667, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30667.0, "min": 16738.0, "max": 32537.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8340750511270016, "min": -0.8678824016276527, "max": -0.5300222679420754, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.690401636064053, "min": -28.291401736438274, "max": -14.310601234436035, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8340750511270016, "min": -0.8678824016276527, "max": -0.5300222679420754, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.690401636064053, "min": -28.291401736438274, "max": -14.310601234436035, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.28844117958215065, "min": 0.28844117958215065, "max": 6.61330724726705, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 9.230117746628821, "min": 8.43572437018156, "max": 112.42622320353985, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679115200", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679115796" }, "total": 595.7575347509999, "count": 1, "self": 0.4817856459998211, "children": { "run_training.setup": { "total": 0.11076482900000428, "count": 1, "self": 0.11076482900000428 }, "TrainerController.start_learning": { "total": 595.164984276, "count": 1, "self": 0.40402751101191825, "children": { "TrainerController._reset_env": { "total": 7.237422566999953, "count": 1, "self": 7.237422566999953 }, "TrainerController.advance": { "total": 587.2881953889881, "count": 18900, "self": 0.44381263899731493, "children": { "env_step": { "total": 399.3241795319849, "count": 18900, "self": 365.52395515697765, "children": { "SubprocessEnvManager._take_step": { "total": 33.546439834997614, "count": 18900, "self": 1.4827796249987841, "children": { "TorchPolicy.evaluate": { "total": 32.06366020999883, "count": 18795, "self": 32.06366020999883 } } }, "workers": { "total": 0.253784540009633, "count": 18900, "self": 0.0, "children": { "worker_root": { "total": 593.6004999339997, "count": 18900, "is_parallel": true, "self": 264.1872149439914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002024562000087826, "count": 1, "is_parallel": true, "self": 0.000679301999866766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013452600002210602, "count": 8, "is_parallel": true, "self": 0.0013452600002210602 } } }, "UnityEnvironment.step": { "total": 0.04842984100002923, "count": 1, "is_parallel": true, "self": 0.0005369990000190228, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005413979999957519, "count": 1, "is_parallel": true, "self": 0.0005413979999957519 }, "communicator.exchange": { "total": 0.04559765800001969, "count": 1, "is_parallel": true, "self": 0.04559765800001969 }, "steps_from_proto": { "total": 0.0017537859999947614, "count": 1, "is_parallel": true, "self": 0.0004373560001340593, "children": { "_process_rank_one_or_two_observation": { "total": 0.001316429999860702, "count": 8, "is_parallel": true, "self": 0.001316429999860702 } } } } } } }, "UnityEnvironment.step": { "total": 329.41328499000826, "count": 18899, "is_parallel": true, "self": 9.387829438018002, "children": { "UnityEnvironment._generate_step_input": { "total": 7.202833267998699, "count": 18899, "is_parallel": true, "self": 7.202833267998699 }, "communicator.exchange": { "total": 283.79601939299323, "count": 18899, "is_parallel": true, "self": 283.79601939299323 }, "steps_from_proto": { "total": 29.026602890998333, "count": 18899, "is_parallel": true, "self": 6.302943624954196, "children": { "_process_rank_one_or_two_observation": { "total": 22.723659266044137, "count": 151192, "is_parallel": true, "self": 22.723659266044137 } } } } } } } } } } }, "trainer_advance": { "total": 187.52020321800592, "count": 18900, "self": 0.6296578120136473, "children": { "process_trajectory": { "total": 35.372208889991384, "count": 18900, "self": 35.372208889991384 }, "_update_policy": { "total": 151.5183365160009, "count": 123, "self": 96.57007124200902, "children": { "TorchPPOOptimizer.update": { "total": 54.948265273991865, "count": 6831, "self": 54.948265273991865 } } } } } } }, "trainer_threads": { "total": 1.0870001005969243e-06, "count": 1, "self": 1.0870001005969243e-06 }, "TrainerController._save_models": { "total": 0.23533772199994019, "count": 1, "self": 0.001340895999874192, "children": { "RLTrainer._checkpoint": { "total": 0.233996826000066, "count": 1, "self": 0.233996826000066 } } } } } } }