ppo-Huggy / run_logs /timers.json
Pavan132's picture
Huggy
0af74ee verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4105726480484009,
"min": 1.4105726480484009,
"max": 1.429369330406189,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70680.9765625,
"min": 68078.8671875,
"max": 77818.3515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.30244755244755,
"min": 82.678391959799,
"max": 407.609756097561,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49365.0,
"min": 48751.0,
"max": 50136.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999946.0,
"min": 49993.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999946.0,
"min": 49993.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.433238983154297,
"min": 0.17993545532226562,
"max": 2.440484046936035,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1391.812744140625,
"min": 21.952125549316406,
"max": 1423.885986328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7358620994157725,
"min": 1.8520400438640938,
"max": 3.928923391145001,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2136.913120865822,
"min": 225.94888535141945,
"max": 2237.1986639499664,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7358620994157725,
"min": 1.8520400438640938,
"max": 3.928923391145001,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2136.913120865822,
"min": 225.94888535141945,
"max": 2237.1986639499664,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014022343472601681,
"min": 0.013395295001888977,
"max": 0.01982601559138857,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.042067030417805046,
"min": 0.026790590003777953,
"max": 0.056103321732856176,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0552152974738015,
"min": 0.02113807378336787,
"max": 0.0641551533093055,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1656458924214045,
"min": 0.04227614756673574,
"max": 0.19246545992791653,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4618488460833413e-06,
"min": 3.4618488460833413e-06,
"max": 0.00029532825155725005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0385546538250024e-05,
"min": 1.0385546538250024e-05,
"max": 0.00084391396869535,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115391666666669,
"min": 0.10115391666666669,
"max": 0.19844275000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034617500000001,
"min": 0.20743775,
"max": 0.5813046500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.758044166666681e-05,
"min": 6.758044166666681e-05,
"max": 0.004922293225000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020274132500000043,
"min": 0.00020274132500000043,
"max": 0.014067102035000001,
"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": "1739291133",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739293535"
},
"total": 2402.008032782,
"count": 1,
"self": 0.4342683350000698,
"children": {
"run_training.setup": {
"total": 0.0235171319999381,
"count": 1,
"self": 0.0235171319999381
},
"TrainerController.start_learning": {
"total": 2401.550247315,
"count": 1,
"self": 4.155285889963125,
"children": {
"TrainerController._reset_env": {
"total": 3.0601832789999435,
"count": 1,
"self": 3.0601832789999435
},
"TrainerController.advance": {
"total": 2394.220499727037,
"count": 231999,
"self": 4.368480947069656,
"children": {
"env_step": {
"total": 1872.7102584710149,
"count": 231999,
"self": 1462.157800464985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.01667669007634,
"count": 231999,
"self": 15.148236136931132,
"children": {
"TorchPolicy.evaluate": {
"total": 392.8684405531452,
"count": 222948,
"self": 392.8684405531452
}
}
},
"workers": {
"total": 2.535781315953386,
"count": 231999,
"self": 0.0,
"children": {
"worker_root": {
"total": 2394.3450850351305,
"count": 231999,
"is_parallel": true,
"self": 1198.9885550510298,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001025017000074513,
"count": 1,
"is_parallel": true,
"self": 0.00034526000001733337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006797570000571795,
"count": 2,
"is_parallel": true,
"self": 0.0006797570000571795
}
}
},
"UnityEnvironment.step": {
"total": 0.030162477000089893,
"count": 1,
"is_parallel": true,
"self": 0.0003202679999958491,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019485900008930912,
"count": 1,
"is_parallel": true,
"self": 0.00019485900008930912
},
"communicator.exchange": {
"total": 0.028941783999925974,
"count": 1,
"is_parallel": true,
"self": 0.028941783999925974
},
"steps_from_proto": {
"total": 0.0007055660000787611,
"count": 1,
"is_parallel": true,
"self": 0.00019090300008883787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005146629999899233,
"count": 2,
"is_parallel": true,
"self": 0.0005146629999899233
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1195.3565299841007,
"count": 231998,
"is_parallel": true,
"self": 36.85608788506033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.13811631506394,
"count": 231998,
"is_parallel": true,
"self": 79.13811631506394
},
"communicator.exchange": {
"total": 994.124324565962,
"count": 231998,
"is_parallel": true,
"self": 994.124324565962
},
"steps_from_proto": {
"total": 85.23800121801457,
"count": 231998,
"is_parallel": true,
"self": 30.129929587110723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.10807163090385,
"count": 463996,
"is_parallel": true,
"self": 55.10807163090385
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.1417603089524,
"count": 231999,
"self": 6.339199613928599,
"children": {
"process_trajectory": {
"total": 157.44089795502327,
"count": 231999,
"self": 156.1521886150233,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2887093399999685,
"count": 10,
"self": 1.2887093399999685
}
}
},
"_update_policy": {
"total": 353.3616627400005,
"count": 97,
"self": 284.15494485700435,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.20671788299614,
"count": 2910,
"self": 69.20671788299614
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.659997886046767e-07,
"count": 1,
"self": 9.659997886046767e-07
},
"TrainerController._save_models": {
"total": 0.11427745300034076,
"count": 1,
"self": 0.0022007590005159727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11207669399982478,
"count": 1,
"self": 0.11207669399982478
}
}
}
}
}
}
}