{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17199361324310303, "min": 0.16023766994476318, "max": 1.517830729484558, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5148.80078125, "min": 4799.53564453125, "max": 46044.9140625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999882.0, "min": 29952.0, "max": 2999882.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999882.0, "min": 29952.0, "max": 2999882.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8424886465072632, "min": -0.1151321604847908, "max": 0.8939157724380493, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 251.9040985107422, "min": -27.631717681884766, "max": 276.219970703125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004798107780516148, "min": -0.018453525379300117, "max": 0.4387224018573761, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4346342086791992, "min": -5.62832498550415, "max": 103.97721099853516, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0485913290024092, "min": 0.042169154122737904, "max": 0.05335811946254883, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3401393030168644, "min": 0.209362885981182, "max": 0.4268649557003906, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013544701179766671, "min": 0.000636581008512578, "max": 0.017399722546716, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0948129082583667, "min": 0.003819486051075468, "max": 0.13549767960406217, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4472709461809541e-06, "min": 1.4472709461809541e-06, "max": 0.00029848320050559997, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.0130896623266679e-05, "min": 1.0130896623266679e-05, "max": 0.0020997929000690667, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048239047619048, "min": 0.10048239047619048, "max": 0.19949440000000002, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7033767333333334, "min": 0.7033767333333334, "max": 1.4999309333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.819080857142863e-05, "min": 5.819080857142863e-05, "max": 0.00994949056, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0004073356600000004, "min": 0.0004073356600000004, "max": 0.07000310024, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007852244190871716, "min": 0.007852244190871716, "max": 0.5107879638671875, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05496571213006973, "min": 0.05496571213006973, "max": 2.04315185546875, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 217.43795620437956, "min": 202.18055555555554, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29789.0, "min": 15984.0, "max": 33301.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7837205774643843, "min": -1.0000000521540642, "max": 1.7969655107835243, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 242.58599853515625, "min": -31.998401686549187, "max": 265.9129976481199, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7837205774643843, "min": -1.0000000521540642, "max": 1.7969655107835243, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 242.58599853515625, "min": -31.998401686549187, "max": 265.9129976481199, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01743386323179199, "min": 0.016626911690852057, "max": 8.99423229880631, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3710053995237104, "min": 2.3710053995237104, "max": 143.90771678090096, "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": "1679466342", "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=Pyramid-PPO --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": "1679473765" }, "total": 7422.513760088, "count": 1, "self": 0.6414520849994005, "children": { "run_training.setup": { "total": 0.10892118099997106, "count": 1, "self": 0.10892118099997106 }, "TrainerController.start_learning": { "total": 7421.763386822, "count": 1, "self": 4.684020906983278, "children": { "TrainerController._reset_env": { "total": 8.805937212000003, "count": 1, "self": 8.805937212000003 }, "TrainerController.advance": { "total": 7408.159792870017, "count": 195509, "self": 5.230926241359157, "children": { "env_step": { "total": 5804.907271271883, "count": 195509, "self": 5451.6062873557885, "children": { "SubprocessEnvManager._take_step": { "total": 350.5550453151157, "count": 195509, "self": 15.1638996301524, "children": { "TorchPolicy.evaluate": { "total": 335.3911456849633, "count": 187551, "self": 335.3911456849633 } } }, "workers": { "total": 2.745938600978775, "count": 195509, "self": 0.0, "children": { "worker_root": { "total": 7403.872047204822, "count": 195509, "is_parallel": true, "self": 2336.202424402918, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004564785000013671, "count": 1, "is_parallel": true, "self": 0.0032543030000056206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013104820000080508, "count": 8, "is_parallel": true, "self": 0.0013104820000080508 } } }, "UnityEnvironment.step": { "total": 0.04972742500001459, "count": 1, "is_parallel": true, "self": 0.0005350890000386244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000507524999989073, "count": 1, "is_parallel": true, "self": 0.000507524999989073 }, "communicator.exchange": { "total": 0.046887311999967096, "count": 1, "is_parallel": true, "self": 0.046887311999967096 }, "steps_from_proto": { "total": 0.0017974990000197977, "count": 1, "is_parallel": true, "self": 0.00037842099993667944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014190780000831182, "count": 8, "is_parallel": true, "self": 0.0014190780000831182 } } } } } } }, "UnityEnvironment.step": { "total": 5067.669622801904, "count": 195508, "is_parallel": true, "self": 98.16029712092586, "children": { "UnityEnvironment._generate_step_input": { "total": 75.98343223986035, "count": 195508, "is_parallel": true, "self": 75.98343223986035 }, "communicator.exchange": { "total": 4585.880222080119, "count": 195508, "is_parallel": true, "self": 4585.880222080119 }, "steps_from_proto": { "total": 307.64567136099845, "count": 195508, "is_parallel": true, "self": 66.92706261661459, "children": { "_process_rank_one_or_two_observation": { "total": 240.71860874438386, "count": 1564064, "is_parallel": true, "self": 240.71860874438386 } } } } } } } } } } }, "trainer_advance": { "total": 1598.0215953567752, "count": 195509, "self": 8.46138777177066, "children": { "process_trajectory": { "total": 394.74153890500685, "count": 195509, "self": 393.99570800600833, "children": { "RLTrainer._checkpoint": { "total": 0.7458308989985198, "count": 6, "self": 0.7458308989985198 } } }, "_update_policy": { "total": 1194.8186686799977, "count": 714, "self": 881.1807643729853, "children": { "TorchPPOOptimizer.update": { "total": 313.6379043070123, "count": 34584, "self": 313.6379043070123 } } } } } } }, "trainer_threads": { "total": 9.539999155094847e-07, "count": 1, "self": 9.539999155094847e-07 }, "TrainerController._save_models": { "total": 0.1136348790005286, "count": 1, "self": 0.0014170140002534026, "children": { "RLTrainer._checkpoint": { "total": 0.1122178650002752, "count": 1, "self": 0.1122178650002752 } } } } } } }