ppo-Huggy / run_logs /timers.json
David0702's picture
Huggy
0260d93 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405356764793396,
"min": 1.405356764793396,
"max": 1.4265131950378418,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71213.640625,
"min": 68603.6484375,
"max": 75391.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.41849529780565,
"min": 77.41849529780565,
"max": 398.57936507936506,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49393.0,
"min": 48679.0,
"max": 50221.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49863.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49863.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4185707569122314,
"min": -0.006573169957846403,
"max": 2.4744482040405273,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1543.048095703125,
"min": -0.8216462731361389,
"max": 1543.048095703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.678571043997349,
"min": 1.8660535373687743,
"max": 3.95278130992283,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2346.9283260703087,
"min": 233.2566921710968,
"max": 2377.865181863308,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.678571043997349,
"min": 1.8660535373687743,
"max": 3.95278130992283,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2346.9283260703087,
"min": 233.2566921710968,
"max": 2377.865181863308,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015438505915689247,
"min": 0.013837885033960145,
"max": 0.019939671092045804,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04631551774706774,
"min": 0.02767577006792029,
"max": 0.05325851211673581,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0660317287262943,
"min": 0.025277748207251233,
"max": 0.0660317287262943,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19809518617888291,
"min": 0.050555496414502465,
"max": 0.19809518617888291,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5026988324666664e-06,
"min": 3.5026988324666664e-06,
"max": 0.0002953395765534749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.05080964974e-05,
"min": 1.05080964974e-05,
"max": 0.00084413656862115,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116753333333334,
"min": 0.10116753333333334,
"max": 0.198446525,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035026,
"min": 0.2075144,
"max": 0.5813788500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.825991333333335e-05,
"min": 6.825991333333335e-05,
"max": 0.0049224815975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020477974000000004,
"min": 0.00020477974000000004,
"max": 0.014070804615,
"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": "1714787139",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714789928"
},
"total": 2789.750142249,
"count": 1,
"self": 0.44332068099993194,
"children": {
"run_training.setup": {
"total": 0.0640124179999475,
"count": 1,
"self": 0.0640124179999475
},
"TrainerController.start_learning": {
"total": 2789.24280915,
"count": 1,
"self": 5.513827500095886,
"children": {
"TrainerController._reset_env": {
"total": 2.971585885999957,
"count": 1,
"self": 2.971585885999957
},
"TrainerController.advance": {
"total": 2780.634362672904,
"count": 232532,
"self": 5.532700237904464,
"children": {
"env_step": {
"total": 2251.1206295579987,
"count": 232532,
"self": 1858.9070997231927,
"children": {
"SubprocessEnvManager._take_step": {
"total": 388.5698675839009,
"count": 232532,
"self": 19.741687620760217,
"children": {
"TorchPolicy.evaluate": {
"total": 368.82817996314066,
"count": 222975,
"self": 368.82817996314066
}
}
},
"workers": {
"total": 3.643662250905095,
"count": 232532,
"self": 0.0,
"children": {
"worker_root": {
"total": 2780.494760547038,
"count": 232532,
"is_parallel": true,
"self": 1295.4731721979608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000872162000064236,
"count": 1,
"is_parallel": true,
"self": 0.00021709899999677873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006550630000674573,
"count": 2,
"is_parallel": true,
"self": 0.0006550630000674573
}
}
},
"UnityEnvironment.step": {
"total": 0.03177551200008111,
"count": 1,
"is_parallel": true,
"self": 0.0003974530001187304,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021440099999381346,
"count": 1,
"is_parallel": true,
"self": 0.00021440099999381346
},
"communicator.exchange": {
"total": 0.030352055999969707,
"count": 1,
"is_parallel": true,
"self": 0.030352055999969707
},
"steps_from_proto": {
"total": 0.0008116019999988566,
"count": 1,
"is_parallel": true,
"self": 0.0002256349999925078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005859670000063488,
"count": 2,
"is_parallel": true,
"self": 0.0005859670000063488
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1485.021588349077,
"count": 232531,
"is_parallel": true,
"self": 44.25557784208877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 95.13061215593211,
"count": 232531,
"is_parallel": true,
"self": 95.13061215593211
},
"communicator.exchange": {
"total": 1239.6496992490543,
"count": 232531,
"is_parallel": true,
"self": 1239.6496992490543
},
"steps_from_proto": {
"total": 105.98569910200194,
"count": 232531,
"is_parallel": true,
"self": 39.616363896048256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.36933520595369,
"count": 465062,
"is_parallel": true,
"self": 66.36933520595369
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 523.9810328770006,
"count": 232532,
"self": 8.385791342020866,
"children": {
"process_trajectory": {
"total": 180.61417722997874,
"count": 232532,
"self": 179.23706570897798,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3771115210007565,
"count": 10,
"self": 1.3771115210007565
}
}
},
"_update_policy": {
"total": 334.98106430500104,
"count": 97,
"self": 269.4272460219951,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.55381828300597,
"count": 2910,
"self": 65.55381828300597
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.479999789618887e-07,
"count": 1,
"self": 9.479999789618887e-07
},
"TrainerController._save_models": {
"total": 0.12303214300027321,
"count": 1,
"self": 0.0020273320001251705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12100481100014804,
"count": 1,
"self": 0.12100481100014804
}
}
}
}
}
}
}