{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4911981523036957,
"min": 0.467925101518631,
"max": 1.09123694896698,
"count": 32
},
"Pyramids.Policy.Entropy.sum": {
"value": 14728.0849609375,
"min": 11893.2548828125,
"max": 32684.73046875,
"count": 32
},
"Pyramids.Step.mean": {
"value": 989969.0,
"min": 59928.0,
"max": 989969.0,
"count": 32
},
"Pyramids.Step.sum": {
"value": 989969.0,
"min": 59928.0,
"max": 989969.0,
"count": 32
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6076779961585999,
"min": -0.10151596367359161,
"max": 0.6076779961585999,
"count": 32
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 168.32679748535156,
"min": -24.36383056640625,
"max": 169.05117797851562,
"count": 32
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005408070981502533,
"min": -0.02192610315978527,
"max": 0.2901652753353119,
"count": 32
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.4980356693267822,
"min": -5.920047760009766,
"max": 54.5532341003418,
"count": 32
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06831378271991283,
"min": 0.06549973934225238,
"max": 0.07371788969074626,
"count": 32
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0247067407986925,
"min": 0.20724000148281144,
"max": 1.1013570397820636,
"count": 32
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014810299799195408,
"min": 0.0007054470476710503,
"max": 0.01644525019946741,
"count": 32
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22215449698793113,
"min": 0.003344204878885648,
"max": 0.23023350279254373,
"count": 32
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4958775014066666e-06,
"min": 7.4958775014066666e-06,
"max": 0.0002836344054552,
"count": 32
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001124381625211,
"min": 0.0001124381625211,
"max": 0.0034903933365355994,
"count": 32
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249859333333332,
"min": 0.10249859333333332,
"max": 0.19454480000000005,
"count": 32
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374788999999998,
"min": 0.5836344000000001,
"max": 2.4856881,
"count": 32
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002596094740000001,
"min": 0.0002596094740000001,
"max": 0.00945502552,
"count": 32
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038941421100000015,
"min": 0.0038941421100000015,
"max": 0.11636009355999999,
"count": 32
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011994203552603722,
"min": 0.011994203552603722,
"max": 0.18642234802246094,
"count": 32
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17991305887699127,
"min": 0.1719922572374344,
"max": 1.131900429725647,
"count": 32
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 32
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 32
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 316.7362637362637,
"min": 294.21153846153845,
"max": 994.1,
"count": 31
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28823.0,
"min": 26130.0,
"max": 33300.0,
"count": 31
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6393010794788927,
"min": -0.9283133847018082,
"max": 1.6865499843485081,
"count": 31
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 149.17639823257923,
"min": -29.600201696157455,
"max": 175.40119837224483,
"count": 31
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6393010794788927,
"min": -0.9283133847018082,
"max": 1.6865499843485081,
"count": 31
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 149.17639823257923,
"min": -29.600201696157455,
"max": 175.40119837224483,
"count": 31
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.039438558429617764,
"min": 0.03741640102648839,
"max": 1.595235589234268,
"count": 31
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5889088170952164,
"min": 3.5889088170952164,
"max": 54.23801003396511,
"count": 31
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1735286846",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training-2 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735288425"
},
"total": 1579.5780913969998,
"count": 1,
"self": 0.3723750139997719,
"children": {
"run_training.setup": {
"total": 0.05844345100013015,
"count": 1,
"self": 0.05844345100013015
},
"TrainerController.start_learning": {
"total": 1579.1472729319999,
"count": 1,
"self": 1.1990838709975833,
"children": {
"TrainerController._reset_env": {
"total": 2.141048976000093,
"count": 1,
"self": 2.141048976000093
},
"TrainerController.advance": {
"total": 1575.728131615003,
"count": 60877,
"self": 1.1340021170117325,
"children": {
"env_step": {
"total": 981.1853453270137,
"count": 60877,
"self": 849.743279197924,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.74169053010246,
"count": 60877,
"self": 3.9887444011742446,
"children": {
"TorchPolicy.evaluate": {
"total": 126.75294612892822,
"count": 59674,
"self": 126.75294612892822
}
}
},
"workers": {
"total": 0.7003755989871934,
"count": 60877,
"self": 0.0,
"children": {
"worker_root": {
"total": 1577.2232645119711,
"count": 60877,
"is_parallel": true,
"self": 813.643860607956,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021291120001478703,
"count": 1,
"is_parallel": true,
"self": 0.0006892149999657704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014398970001820999,
"count": 8,
"is_parallel": true,
"self": 0.0014398970001820999
}
}
},
"UnityEnvironment.step": {
"total": 0.03558809800006202,
"count": 1,
"is_parallel": true,
"self": 0.00043798999968203134,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002976790001412155,
"count": 1,
"is_parallel": true,
"self": 0.0002976790001412155
},
"communicator.exchange": {
"total": 0.03369493700029125,
"count": 1,
"is_parallel": true,
"self": 0.03369493700029125
},
"steps_from_proto": {
"total": 0.0011574919999475242,
"count": 1,
"is_parallel": true,
"self": 0.00026514599903748604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008923460009100381,
"count": 8,
"is_parallel": true,
"self": 0.0008923460009100381
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 763.5794039040152,
"count": 60876,
"is_parallel": true,
"self": 20.026678129896027,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.234710094981438,
"count": 60876,
"is_parallel": true,
"self": 13.234710094981438
},
"communicator.exchange": {
"total": 670.9992639440088,
"count": 60876,
"is_parallel": true,
"self": 670.9992639440088
},
"steps_from_proto": {
"total": 59.3187517351289,
"count": 60876,
"is_parallel": true,
"self": 12.769690017142693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.549061717986206,
"count": 487008,
"is_parallel": true,
"self": 46.549061717986206
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 593.4087841709775,
"count": 60877,
"self": 2.342837882875301,
"children": {
"process_trajectory": {
"total": 110.39465231010354,
"count": 60877,
"self": 110.20503664010312,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18961567000042123,
"count": 2,
"self": 0.18961567000042123
}
}
},
"_update_policy": {
"total": 480.67129397799863,
"count": 437,
"self": 263.5983995040906,
"children": {
"TorchPPOOptimizer.update": {
"total": 217.07289447390804,
"count": 21753,
"self": 217.07289447390804
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0969997674692422e-06,
"count": 1,
"self": 1.0969997674692422e-06
},
"TrainerController._save_models": {
"total": 0.07900737299951288,
"count": 1,
"self": 0.0018110769997292664,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07719629599978362,
"count": 1,
"self": 0.07719629599978362
}
}
}
}
}
}
}