{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13812561333179474, "min": 0.1300668865442276, "max": 1.3911514282226562, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4165.86865234375, "min": 3908.25, "max": 42201.96875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999937.0, "min": 29952.0, "max": 2999937.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7037657499313354, "min": -0.1038188636302948, "max": 0.7569353580474854, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 202.68453979492188, "min": -25.124164581298828, "max": 223.29592895507812, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008098602294921875, "min": -0.02800179459154606, "max": 0.3554890751838684, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3323974609375, "min": -7.000448703765869, "max": 85.31737518310547, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06942759208652051, "min": 0.06459752663726076, "max": 0.07470682326448932, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0414138812978075, "min": 0.5026395184771711, "max": 1.0920484330757365, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015140128954164563, "min": 0.000559156469113454, "max": 0.015209308382904211, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22710193431246845, "min": 0.007828190567588357, "max": 0.22710193431246845, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5261328246555497e-06, "min": 1.5261328246555497e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2891992369833245e-05, "min": 2.2891992369833245e-05, "max": 0.004072499642500166, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050867777777778, "min": 0.10050867777777778, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5076301666666667, "min": 1.3962282666666668, "max": 2.8574998333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.081690999999982e-05, "min": 6.081690999999982e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009122536499999973, "min": 0.0009122536499999973, "max": 0.13576423334999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006364238448441029, "min": 0.006207617931067944, "max": 0.4950527548789978, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0954635739326477, "min": 0.08690664917230606, "max": 3.46536922454834, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 262.13157894736844, "min": 248.6283185840708, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29883.0, "min": 15984.0, "max": 32816.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7027736698326312, "min": -1.0000000521540642, "max": 1.7493643871808455, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 194.11619836091995, "min": -30.366201736032963, "max": 207.8499983996153, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7027736698326312, "min": -1.0000000521540642, "max": 1.7493643871808455, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 194.11619836091995, "min": -30.366201736032963, "max": 207.8499983996153, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017543459846484966, "min": 0.016231927010580995, "max": 9.283691899850965, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.999954422499286, "min": 1.8342077521956526, "max": 148.53907039761543, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679165695", "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": "1679172480" }, "total": 6784.774292673001, "count": 1, "self": 0.8284274229999937, "children": { "run_training.setup": { "total": 0.10113743099998374, "count": 1, "self": 0.10113743099998374 }, "TrainerController.start_learning": { "total": 6783.844727819001, "count": 1, "self": 4.311673362785768, "children": { "TrainerController._reset_env": { "total": 9.288895310000015, "count": 1, "self": 9.288895310000015 }, "TrainerController.advance": { "total": 6770.097951433215, "count": 194104, "self": 4.485844236297453, "children": { "env_step": { "total": 4912.637607128945, "count": 194104, "self": 4583.326478295069, "children": { "SubprocessEnvManager._take_step": { "total": 326.6527773858652, "count": 194104, "self": 14.097604768669953, "children": { "TorchPolicy.evaluate": { "total": 312.55517261719524, "count": 187560, "self": 312.55517261719524 } } }, "workers": { "total": 2.6583514480105634, "count": 194104, "self": 0.0, "children": { "worker_root": { "total": 6769.018071587179, "count": 194104, "is_parallel": true, "self": 2540.4636443200798, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004803646999988587, "count": 1, "is_parallel": true, "self": 0.0034361030000127357, "children": { "_process_rank_one_or_two_observation": { "total": 0.001367543999975851, "count": 8, "is_parallel": true, "self": 0.001367543999975851 } } }, "UnityEnvironment.step": { "total": 0.04461865999999759, "count": 1, "is_parallel": true, "self": 0.00051388299999644, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004580529999884675, "count": 1, "is_parallel": true, "self": 0.0004580529999884675 }, "communicator.exchange": { "total": 0.04208371800001487, "count": 1, "is_parallel": true, "self": 0.04208371800001487 }, "steps_from_proto": { "total": 0.001563005999997813, "count": 1, "is_parallel": true, "self": 0.00035665699994069655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012063490000571164, "count": 8, "is_parallel": true, "self": 0.0012063490000571164 } } } } } } }, "UnityEnvironment.step": { "total": 4228.5544272670995, "count": 194103, "is_parallel": true, "self": 94.1515808195536, "children": { "UnityEnvironment._generate_step_input": { "total": 67.25315761779191, "count": 194103, "is_parallel": true, "self": 67.25315761779191 }, "communicator.exchange": { "total": 3792.627446403854, "count": 194103, "is_parallel": true, "self": 3792.627446403854 }, "steps_from_proto": { "total": 274.5222424258999, "count": 194103, "is_parallel": true, "self": 59.04667306158797, "children": { "_process_rank_one_or_two_observation": { "total": 215.47556936431192, "count": 1552824, "is_parallel": true, "self": 215.47556936431192 } } } } } } } } } } }, "trainer_advance": { "total": 1852.9745000679727, "count": 194104, "self": 8.787918639768122, "children": { "process_trajectory": { "total": 358.04258003919983, "count": 194104, "self": 357.40864835820037, "children": { "RLTrainer._checkpoint": { "total": 0.6339316809994671, "count": 6, "self": 0.6339316809994671 } } }, "_update_policy": { "total": 1486.1440013890049, "count": 1403, "self": 948.8243581499814, "children": { "TorchPPOOptimizer.update": { "total": 537.3196432390234, "count": 68364, "self": 537.3196432390234 } } } } } } }, "trainer_threads": { "total": 1.1719994290615432e-06, "count": 1, "self": 1.1719994290615432e-06 }, "TrainerController._save_models": { "total": 0.14620654100053798, "count": 1, "self": 0.001961514000868192, "children": { "RLTrainer._checkpoint": { "total": 0.1442450269996698, "count": 1, "self": 0.1442450269996698 } } } } } } }