ppo-Pyramids / run_logs /timers.json
migolan's picture
First Push
863b0b7 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.575046181678772,
"min": 0.575046181678772,
"max": 1.496279001235962,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17297.388671875,
"min": 17297.388671875,
"max": 45391.12109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4556284546852112,
"min": -0.10446827858686447,
"max": 0.518004834651947,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 123.47531127929688,
"min": -25.0723876953125,
"max": 142.3546905517578,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03360367566347122,
"min": -0.21482953429222107,
"max": 0.25233009457588196,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.106595993041992,
"min": -59.29294967651367,
"max": 60.811553955078125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06887413755563708,
"min": 0.06416696780231884,
"max": 0.07440807647057256,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0331120633345563,
"min": 0.5031662845064822,
"max": 1.0470170738590951,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01735562961532398,
"min": 0.0007068046891796272,
"max": 0.01808175273479373,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2603344442298597,
"min": 0.00989526564851478,
"max": 0.2603344442298597,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.552357482580003e-06,
"min": 7.552357482580003e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011328536223870004,
"min": 0.00011328536223870004,
"max": 0.0035072909309030995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251742000000001,
"min": 0.10251742000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5377613,
"min": 1.3886848,
"max": 2.5690969,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026149025800000007,
"min": 0.00026149025800000007,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003922353870000001,
"min": 0.003922353870000001,
"max": 0.11693278031000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009901696816086769,
"min": 0.009901696816086769,
"max": 0.3709532618522644,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1485254466533661,
"min": 0.14177252352237701,
"max": 2.596672773361206,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 376.4125,
"min": 367.109756097561,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30113.0,
"min": 15984.0,
"max": 34148.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5485574770718813,
"min": -1.0000000521540642,
"max": 1.5485574770718813,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 123.8845981657505,
"min": -29.589601643383503,
"max": 123.89379841089249,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5485574770718813,
"min": -1.0000000521540642,
"max": 1.5485574770718813,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 123.8845981657505,
"min": -29.589601643383503,
"max": 123.89379841089249,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.038798593003230054,
"min": 0.03861667232647561,
"max": 7.1294049844145775,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1038874402584042,
"min": 3.102773234479173,
"max": 114.07047975063324,
"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": "1737302276",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737304478"
},
"total": 2201.832821393,
"count": 1,
"self": 0.588602864999757,
"children": {
"run_training.setup": {
"total": 0.02275929699999324,
"count": 1,
"self": 0.02275929699999324
},
"TrainerController.start_learning": {
"total": 2201.221459231,
"count": 1,
"self": 1.2841939490344885,
"children": {
"TrainerController._reset_env": {
"total": 2.719813302000034,
"count": 1,
"self": 2.719813302000034
},
"TrainerController.advance": {
"total": 2197.130781382966,
"count": 63599,
"self": 1.4422899929973028,
"children": {
"env_step": {
"total": 1527.2048724359774,
"count": 63599,
"self": 1375.3169736019554,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.11844526802025,
"count": 63599,
"self": 4.736378983024963,
"children": {
"TorchPolicy.evaluate": {
"total": 146.3820662849953,
"count": 62551,
"self": 146.3820662849953
}
}
},
"workers": {
"total": 0.7694535660017436,
"count": 63599,
"self": 0.0,
"children": {
"worker_root": {
"total": 2196.191129993962,
"count": 63599,
"is_parallel": true,
"self": 934.7456933909475,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005563602999984596,
"count": 1,
"is_parallel": true,
"self": 0.004171089999999822,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001392512999984774,
"count": 8,
"is_parallel": true,
"self": 0.001392512999984774
}
}
},
"UnityEnvironment.step": {
"total": 0.07759031800003413,
"count": 1,
"is_parallel": true,
"self": 0.0009456870000121853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042887699999027973,
"count": 1,
"is_parallel": true,
"self": 0.00042887699999027973
},
"communicator.exchange": {
"total": 0.07437891400002172,
"count": 1,
"is_parallel": true,
"self": 0.07437891400002172
},
"steps_from_proto": {
"total": 0.0018368400000099427,
"count": 1,
"is_parallel": true,
"self": 0.0005012830000055146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013355570000044281,
"count": 8,
"is_parallel": true,
"self": 0.0013355570000044281
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.4454366030145,
"count": 63598,
"is_parallel": true,
"self": 31.958794295029065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.034628188025124,
"count": 63598,
"is_parallel": true,
"self": 23.034628188025124
},
"communicator.exchange": {
"total": 1110.7467719710205,
"count": 63598,
"is_parallel": true,
"self": 1110.7467719710205
},
"steps_from_proto": {
"total": 95.70524214893976,
"count": 63598,
"is_parallel": true,
"self": 19.132105483846033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.57313666509373,
"count": 508784,
"is_parallel": true,
"self": 76.57313666509373
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 668.483618953991,
"count": 63599,
"self": 2.5508022310568776,
"children": {
"process_trajectory": {
"total": 127.99392449693505,
"count": 63599,
"self": 127.71715466193496,
"children": {
"RLTrainer._checkpoint": {
"total": 0.27676983500009555,
"count": 2,
"self": 0.27676983500009555
}
}
},
"_update_policy": {
"total": 537.9388922259991,
"count": 451,
"self": 296.28583388202173,
"children": {
"TorchPPOOptimizer.update": {
"total": 241.65305834397736,
"count": 22761,
"self": 241.65305834397736
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.229997885995544e-07,
"count": 1,
"self": 9.229997885995544e-07
},
"TrainerController._save_models": {
"total": 0.08666967399994974,
"count": 1,
"self": 0.0014553480000358832,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08521432599991385,
"count": 1,
"self": 0.08521432599991385
}
}
}
}
}
}
}