ppo-Huggy / run_logs /timers.json
Umang-Bansal's picture
Huggy
7ab21c6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055426120758057,
"min": 1.4055426120758057,
"max": 1.4268487691879272,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69616.5234375,
"min": 68696.4296875,
"max": 77991.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.7384370015949,
"min": 70.97697841726618,
"max": 433.9568965517241,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 48835.0,
"max": 50339.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49812.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49812.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5089101791381836,
"min": 0.13317498564720154,
"max": 2.547895908355713,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1573.086669921875,
"min": 15.315122604370117,
"max": 1713.9921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8154970703132607,
"min": 2.008167176661284,
"max": 4.144100685844888,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2392.3166630864143,
"min": 230.93922531604767,
"max": 2710.7516180872917,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8154970703132607,
"min": 2.008167176661284,
"max": 4.144100685844888,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2392.3166630864143,
"min": 230.93922531604767,
"max": 2710.7516180872917,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0169853576064472,
"min": 0.013692388426231142,
"max": 0.020872389979841602,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0509560728193416,
"min": 0.027384776852462284,
"max": 0.0626171699395248,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054448790268765555,
"min": 0.021760912643124658,
"max": 0.06458737117548784,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16334637080629666,
"min": 0.043521825286249316,
"max": 0.18395906363924344,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.713698762133328e-06,
"min": 3.713698762133328e-06,
"max": 0.0002953347015551,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1141096286399984e-05,
"min": 1.1141096286399984e-05,
"max": 0.0008441473686175501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123786666666663,
"min": 0.10123786666666663,
"max": 0.19844490000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037135999999999,
"min": 0.20760730000000005,
"max": 0.58138245,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.176954666666658e-05,
"min": 7.176954666666658e-05,
"max": 0.004922400510000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021530863999999974,
"min": 0.00021530863999999974,
"max": 0.014070984255000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720712285",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720714812"
},
"total": 2526.772394758,
"count": 1,
"self": 0.48067271699983394,
"children": {
"run_training.setup": {
"total": 0.057258781999991015,
"count": 1,
"self": 0.057258781999991015
},
"TrainerController.start_learning": {
"total": 2526.2344632589998,
"count": 1,
"self": 4.478449271011868,
"children": {
"TrainerController._reset_env": {
"total": 2.9491777740000202,
"count": 1,
"self": 2.9491777740000202
},
"TrainerController.advance": {
"total": 2518.691660253988,
"count": 233330,
"self": 4.8353500789862665,
"children": {
"env_step": {
"total": 1994.7536572240235,
"count": 233330,
"self": 1651.8962269460085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.81158764295424,
"count": 233330,
"self": 16.96804121195754,
"children": {
"TorchPolicy.evaluate": {
"total": 322.8435464309967,
"count": 222968,
"self": 322.8435464309967
}
}
},
"workers": {
"total": 3.045842635060694,
"count": 233330,
"self": 0.0,
"children": {
"worker_root": {
"total": 2518.6057707750283,
"count": 233330,
"is_parallel": true,
"self": 1188.7470513249407,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000930262999986553,
"count": 1,
"is_parallel": true,
"self": 0.0002436780000039107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006865849999826423,
"count": 2,
"is_parallel": true,
"self": 0.0006865849999826423
}
}
},
"UnityEnvironment.step": {
"total": 0.032604481000021224,
"count": 1,
"is_parallel": true,
"self": 0.0004434549999814408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022822300002189877,
"count": 1,
"is_parallel": true,
"self": 0.00022822300002189877
},
"communicator.exchange": {
"total": 0.030884185999980218,
"count": 1,
"is_parallel": true,
"self": 0.030884185999980218
},
"steps_from_proto": {
"total": 0.001048617000037666,
"count": 1,
"is_parallel": true,
"self": 0.0002525329999798487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007960840000578173,
"count": 2,
"is_parallel": true,
"self": 0.0007960840000578173
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.8587194500876,
"count": 233329,
"is_parallel": true,
"self": 40.01052971609852,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.45264619697815,
"count": 233329,
"is_parallel": true,
"self": 87.45264619697815
},
"communicator.exchange": {
"total": 1109.0191897579668,
"count": 233329,
"is_parallel": true,
"self": 1109.0191897579668
},
"steps_from_proto": {
"total": 93.37635377904422,
"count": 233329,
"is_parallel": true,
"self": 35.05463492900782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.321718850036405,
"count": 466658,
"is_parallel": true,
"self": 58.321718850036405
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 519.1026529509783,
"count": 233330,
"self": 6.75817338200784,
"children": {
"process_trajectory": {
"total": 167.0741923869707,
"count": 233330,
"self": 166.25832327497096,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8158691119997457,
"count": 6,
"self": 0.8158691119997457
}
}
},
"_update_policy": {
"total": 345.27028718199966,
"count": 97,
"self": 280.0630513360013,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.20723584599835,
"count": 2910,
"self": 65.20723584599835
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.002999852062203e-06,
"count": 1,
"self": 1.002999852062203e-06
},
"TrainerController._save_models": {
"total": 0.11517495699990832,
"count": 1,
"self": 0.0021243479995973757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11305060900031094,
"count": 1,
"self": 0.11305060900031094
}
}
}
}
}
}
}