ppo-Huggy / run_logs /timers.json
Milad-R's picture
Huggy
9752d18 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4013895988464355,
"min": 1.4013895988464355,
"max": 1.4241212606430054,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69877.4921875,
"min": 67827.5,
"max": 75699.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.47126436781609,
"min": 85.57192374350086,
"max": 402.792,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49836.0,
"min": 48915.0,
"max": 50349.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999655.0,
"min": 49724.0,
"max": 1999655.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999655.0,
"min": 49724.0,
"max": 1999655.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.437317132949829,
"min": 0.004788610152900219,
"max": 2.488913059234619,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1272.279541015625,
"min": 0.593787670135498,
"max": 1386.8087158203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8044906437853743,
"min": 1.8862385833936353,
"max": 3.910315608381119,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1985.9441160559654,
"min": 233.89358434081078,
"max": 2166.794036269188,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8044906437853743,
"min": 1.8862385833936353,
"max": 3.910315608381119,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1985.9441160559654,
"min": 233.89358434081078,
"max": 2166.794036269188,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.012850921869216513,
"min": 0.012850921869216513,
"max": 0.019001457554986702,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03855276560764954,
"min": 0.027462646514535057,
"max": 0.0554017250367906,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05261066307624181,
"min": 0.023930359197159606,
"max": 0.06117468741205004,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15783198922872543,
"min": 0.04786071839431921,
"max": 0.18352406223615012,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2167989277666723e-06,
"min": 3.2167989277666723e-06,
"max": 0.0002953159515613499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.650396783300017e-06,
"min": 9.650396783300017e-06,
"max": 0.0008438949187016999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107223333333333,
"min": 0.10107223333333333,
"max": 0.19843865,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032167,
"min": 0.20728555,
"max": 0.5812983,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.350444333333342e-05,
"min": 6.350444333333342e-05,
"max": 0.004922088635,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019051333000000026,
"min": 0.00019051333000000026,
"max": 0.01406678517,
"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": "1719052923",
"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": "1719055524"
},
"total": 2601.6882195119997,
"count": 1,
"self": 0.4425503279999248,
"children": {
"run_training.setup": {
"total": 0.05684359499991842,
"count": 1,
"self": 0.05684359499991842
},
"TrainerController.start_learning": {
"total": 2601.188825589,
"count": 1,
"self": 4.70372700203643,
"children": {
"TrainerController._reset_env": {
"total": 2.85776786800011,
"count": 1,
"self": 2.85776786800011
},
"TrainerController.advance": {
"total": 2593.506942002963,
"count": 232113,
"self": 4.972126386909622,
"children": {
"env_step": {
"total": 2047.722219943,
"count": 232113,
"self": 1691.1180927928776,
"children": {
"SubprocessEnvManager._take_step": {
"total": 353.4729097540726,
"count": 232113,
"self": 19.022782061013913,
"children": {
"TorchPolicy.evaluate": {
"total": 334.4501276930587,
"count": 222914,
"self": 334.4501276930587
}
}
},
"workers": {
"total": 3.1312173960498058,
"count": 232113,
"self": 0.0,
"children": {
"worker_root": {
"total": 2593.816346413964,
"count": 232113,
"is_parallel": true,
"self": 1227.143324318965,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009381780000694562,
"count": 1,
"is_parallel": true,
"self": 0.0002274880000641133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007106900000053429,
"count": 2,
"is_parallel": true,
"self": 0.0007106900000053429
}
}
},
"UnityEnvironment.step": {
"total": 0.03373661399996308,
"count": 1,
"is_parallel": true,
"self": 0.00037203399983809504,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021910500004196365,
"count": 1,
"is_parallel": true,
"self": 0.00021910500004196365
},
"communicator.exchange": {
"total": 0.03238377299999229,
"count": 1,
"is_parallel": true,
"self": 0.03238377299999229
},
"steps_from_proto": {
"total": 0.000761702000090736,
"count": 1,
"is_parallel": true,
"self": 0.00020227000027261965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005594319998181163,
"count": 2,
"is_parallel": true,
"self": 0.0005594319998181163
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1366.673022094999,
"count": 232112,
"is_parallel": true,
"self": 40.586277329854056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.42606058905494,
"count": 232112,
"is_parallel": true,
"self": 90.42606058905494
},
"communicator.exchange": {
"total": 1139.3428632009673,
"count": 232112,
"is_parallel": true,
"self": 1139.3428632009673
},
"steps_from_proto": {
"total": 96.31782097512269,
"count": 232112,
"is_parallel": true,
"self": 36.47295184028667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.84486913483602,
"count": 464224,
"is_parallel": true,
"self": 59.84486913483602
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 540.8125956730537,
"count": 232113,
"self": 7.032669174093144,
"children": {
"process_trajectory": {
"total": 165.16464988196117,
"count": 232113,
"self": 163.8585730609616,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3060768209995786,
"count": 10,
"self": 1.3060768209995786
}
}
},
"_update_policy": {
"total": 368.6152766169994,
"count": 97,
"self": 302.11669205800854,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.49858455899084,
"count": 2910,
"self": 66.49858455899084
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.919999683916103e-07,
"count": 1,
"self": 9.919999683916103e-07
},
"TrainerController._save_models": {
"total": 0.12038772400001108,
"count": 1,
"self": 0.0020347149998087843,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11835300900020229,
"count": 1,
"self": 0.11835300900020229
}
}
}
}
}
}
}