ppo-Huggy / run_logs /timers.json
mhdaw's picture
Huggy
4c0d266
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404681921005249,
"min": 1.404681921005249,
"max": 1.4264096021652222,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70797.375,
"min": 67617.984375,
"max": 75700.3828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.28445747800586,
"min": 72.28445747800586,
"max": 354.2695035460993,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49298.0,
"min": 49253.0,
"max": 49952.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999931.0,
"min": 49944.0,
"max": 1999931.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999931.0,
"min": 49944.0,
"max": 1999931.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4276773929595947,
"min": 0.061893388628959656,
"max": 2.469327688217163,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1655.676025390625,
"min": 8.665074348449707,
"max": 1655.676025390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8299601101630594,
"min": 1.8457670961107526,
"max": 4.085269452952549,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2612.0327951312065,
"min": 258.40739345550537,
"max": 2612.0327951312065,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8299601101630594,
"min": 1.8457670961107526,
"max": 4.085269452952549,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2612.0327951312065,
"min": 258.40739345550537,
"max": 2612.0327951312065,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01896534822557846,
"min": 0.012667089529713849,
"max": 0.02270372000154263,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056896044676735376,
"min": 0.025334179059427697,
"max": 0.06158830055889364,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.07049726487861739,
"min": 0.023504732487102352,
"max": 0.07049726487861739,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.2114917946358522,
"min": 0.047009464974204704,
"max": 0.2114917946358522,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.833448722216681e-06,
"min": 3.833448722216681e-06,
"max": 0.00029531550156149995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1500346166650043e-05,
"min": 1.1500346166650043e-05,
"max": 0.00084388786870405,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127778333333336,
"min": 0.10127778333333336,
"max": 0.1984385,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30383335000000006,
"min": 0.20768615000000007,
"max": 0.5812959499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.376138833333355e-05,
"min": 7.376138833333355e-05,
"max": 0.0049220811499999986,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022128416500000065,
"min": 0.00022128416500000065,
"max": 0.014066667905000002,
"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": "1690939837",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690942307"
},
"total": 2469.453077994,
"count": 1,
"self": 0.7333301510002457,
"children": {
"run_training.setup": {
"total": 0.06344446800000014,
"count": 1,
"self": 0.06344446800000014
},
"TrainerController.start_learning": {
"total": 2468.656303375,
"count": 1,
"self": 4.532159792958737,
"children": {
"TrainerController._reset_env": {
"total": 6.181505899000001,
"count": 1,
"self": 6.181505899000001
},
"TrainerController.advance": {
"total": 2457.756425467041,
"count": 232699,
"self": 4.555917009055975,
"children": {
"env_step": {
"total": 1899.2454625619428,
"count": 232699,
"self": 1602.3931688200096,
"children": {
"SubprocessEnvManager._take_step": {
"total": 293.9857234269673,
"count": 232699,
"self": 16.460233606938857,
"children": {
"TorchPolicy.evaluate": {
"total": 277.52548982002844,
"count": 222898,
"self": 277.52548982002844
}
}
},
"workers": {
"total": 2.86657031496577,
"count": 232699,
"self": 0.0,
"children": {
"worker_root": {
"total": 2461.1322040899377,
"count": 232699,
"is_parallel": true,
"self": 1150.0446210638338,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010121270000240656,
"count": 1,
"is_parallel": true,
"self": 0.0002562299999908646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000755897000033201,
"count": 2,
"is_parallel": true,
"self": 0.000755897000033201
}
}
},
"UnityEnvironment.step": {
"total": 0.029292880000014065,
"count": 1,
"is_parallel": true,
"self": 0.0003200520000063989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022357599999622835,
"count": 1,
"is_parallel": true,
"self": 0.00022357599999622835
},
"communicator.exchange": {
"total": 0.02792044400001714,
"count": 1,
"is_parallel": true,
"self": 0.02792044400001714
},
"steps_from_proto": {
"total": 0.0008288079999942966,
"count": 1,
"is_parallel": true,
"self": 0.00024209899999050322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005867090000037933,
"count": 2,
"is_parallel": true,
"self": 0.0005867090000037933
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.0875830261039,
"count": 232698,
"is_parallel": true,
"self": 40.159352146057245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.1543507289644,
"count": 232698,
"is_parallel": true,
"self": 82.1543507289644
},
"communicator.exchange": {
"total": 1089.880879019063,
"count": 232698,
"is_parallel": true,
"self": 1089.880879019063
},
"steps_from_proto": {
"total": 98.8930011320191,
"count": 232698,
"is_parallel": true,
"self": 35.3052452090547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.58775592296439,
"count": 465396,
"is_parallel": true,
"self": 63.58775592296439
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 553.9550458960425,
"count": 232699,
"self": 6.632296845031192,
"children": {
"process_trajectory": {
"total": 140.08354379201103,
"count": 232699,
"self": 138.7363360420112,
"children": {
"RLTrainer._checkpoint": {
"total": 1.347207749999825,
"count": 10,
"self": 1.347207749999825
}
}
},
"_update_policy": {
"total": 407.2392052590003,
"count": 97,
"self": 347.0380034329908,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.20120182600948,
"count": 2910,
"self": 60.20120182600948
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3220001164881978e-06,
"count": 1,
"self": 1.3220001164881978e-06
},
"TrainerController._save_models": {
"total": 0.18621089399994162,
"count": 1,
"self": 0.002825828999903024,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1833850650000386,
"count": 1,
"self": 0.1833850650000386
}
}
}
}
}
}
}