ppo-Huggy / run_logs /timers.json
gael1130's picture
Huggy
297969e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070351123809814,
"min": 1.4070351123809814,
"max": 1.4288113117218018,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72096.4765625,
"min": 67641.5546875,
"max": 77039.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.10303030303031,
"min": 80.34146341463415,
"max": 379.01503759398497,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50046.0,
"min": 48789.0,
"max": 50409.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999896.0,
"min": 49904.0,
"max": 1999896.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999896.0,
"min": 49904.0,
"max": 1999896.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4080214500427246,
"min": 0.0691513866186142,
"max": 2.4819653034210205,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1191.9705810546875,
"min": 9.127983093261719,
"max": 1471.8446044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.607967947829853,
"min": 1.6853504715995355,
"max": 4.056688231633881,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1785.9441341757774,
"min": 222.4662622511387,
"max": 2393.44605666399,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.607967947829853,
"min": 1.6853504715995355,
"max": 4.056688231633881,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1785.9441341757774,
"min": 222.4662622511387,
"max": 2393.44605666399,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015821912555838934,
"min": 0.013262534732348286,
"max": 0.021437966507073726,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04746573766751681,
"min": 0.02652506946469657,
"max": 0.05455798719194718,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05936468897594346,
"min": 0.02264649427185456,
"max": 0.05936468897594346,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17809406692783036,
"min": 0.04529298854370912,
"max": 0.17809406692783036,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.353348882249997e-06,
"min": 3.353348882249997e-06,
"max": 0.00029538292653902493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.006004664674999e-05,
"min": 1.006004664674999e-05,
"max": 0.00084426706857765,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111775000000002,
"min": 0.10111775000000002,
"max": 0.19846097499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033532500000001,
"min": 0.20737150000000007,
"max": 0.5814223500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.577572499999995e-05,
"min": 6.577572499999995e-05,
"max": 0.0049232026525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019732717499999983,
"min": 0.00019732717499999983,
"max": 0.014072975264999999,
"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": "1707167685",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707170094"
},
"total": 2408.776927227,
"count": 1,
"self": 0.395263963999696,
"children": {
"run_training.setup": {
"total": 0.05145957400009138,
"count": 1,
"self": 0.05145957400009138
},
"TrainerController.start_learning": {
"total": 2408.3302036890004,
"count": 1,
"self": 4.658158135017402,
"children": {
"TrainerController._reset_env": {
"total": 3.0136501269998917,
"count": 1,
"self": 3.0136501269998917
},
"TrainerController.advance": {
"total": 2400.5374696559825,
"count": 232633,
"self": 4.976174993229961,
"children": {
"env_step": {
"total": 1936.6356504668383,
"count": 232633,
"self": 1591.3879358678728,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.3831602209284,
"count": 232633,
"self": 16.375016087897166,
"children": {
"TorchPolicy.evaluate": {
"total": 326.00814413303124,
"count": 223058,
"self": 326.00814413303124
}
}
},
"workers": {
"total": 2.8645543780371554,
"count": 232633,
"self": 0.0,
"children": {
"worker_root": {
"total": 2400.835420867929,
"count": 232633,
"is_parallel": true,
"self": 1109.4815888948983,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008870569999999134,
"count": 1,
"is_parallel": true,
"self": 0.00023569299992232118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006513640000775922,
"count": 2,
"is_parallel": true,
"self": 0.0006513640000775922
}
}
},
"UnityEnvironment.step": {
"total": 0.035962236000159464,
"count": 1,
"is_parallel": true,
"self": 0.0003199770003448066,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0056272140000146464,
"count": 1,
"is_parallel": true,
"self": 0.0056272140000146464
},
"communicator.exchange": {
"total": 0.029297865999978967,
"count": 1,
"is_parallel": true,
"self": 0.029297865999978967
},
"steps_from_proto": {
"total": 0.0007171789998210443,
"count": 1,
"is_parallel": true,
"self": 0.00019572299970604945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005214560001149948,
"count": 2,
"is_parallel": true,
"self": 0.0005214560001149948
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.3538319730305,
"count": 232632,
"is_parallel": true,
"self": 40.76395329984007,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.6485411791964,
"count": 232632,
"is_parallel": true,
"self": 88.6485411791964
},
"communicator.exchange": {
"total": 1069.589074896062,
"count": 232632,
"is_parallel": true,
"self": 1069.589074896062
},
"steps_from_proto": {
"total": 92.35226259793217,
"count": 232632,
"is_parallel": true,
"self": 34.59302033581207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.7592422621201,
"count": 465264,
"is_parallel": true,
"self": 57.7592422621201
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 458.9256441959142,
"count": 232633,
"self": 6.782251818973236,
"children": {
"process_trajectory": {
"total": 157.80385947394416,
"count": 232633,
"self": 156.50154561094405,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3023138630001085,
"count": 10,
"self": 1.3023138630001085
}
}
},
"_update_policy": {
"total": 294.3395329029968,
"count": 97,
"self": 242.69656993303033,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.64296296996645,
"count": 2910,
"self": 51.64296296996645
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.639999578008428e-07,
"count": 1,
"self": 8.639999578008428e-07
},
"TrainerController._save_models": {
"total": 0.12092490700069902,
"count": 1,
"self": 0.002421692000098119,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1185032150006009,
"count": 1,
"self": 0.1185032150006009
}
}
}
}
}
}
}