ppo-Huggy / run_logs /timers.json
RicardoMorim's picture
Huggy
f49226b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3850798606872559,
"min": 1.3850798606872559,
"max": 1.4262372255325317,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69309.3984375,
"min": 68396.4921875,
"max": 77440.0703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.06846846846847,
"min": 86.75909878682842,
"max": 396.6190476190476,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 48846.0,
"max": 50060.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49558.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49558.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4148404598236084,
"min": 0.10925135761499405,
"max": 2.4148404598236084,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1340.2364501953125,
"min": 13.65641975402832,
"max": 1370.0167236328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8347639841002388,
"min": 1.802836715221405,
"max": 3.8835139886854084,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2128.2940111756325,
"min": 225.35458940267563,
"max": 2145.465824365616,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8347639841002388,
"min": 1.802836715221405,
"max": 3.8835139886854084,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2128.2940111756325,
"min": 225.35458940267563,
"max": 2145.465824365616,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016805815245364404,
"min": 0.014514927986844365,
"max": 0.020268985023238883,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05041744573609321,
"min": 0.029531006969773444,
"max": 0.05746127926104236,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05667940567558011,
"min": 0.025713309762068093,
"max": 0.05955011858604848,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17003821702674032,
"min": 0.051426619524136186,
"max": 0.17003821702674032,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.412348862583328e-06,
"min": 3.412348862583328e-06,
"max": 0.00029529825156724993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0237046587749983e-05,
"min": 1.0237046587749983e-05,
"max": 0.0008437926187357999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113741666666669,
"min": 0.10113741666666669,
"max": 0.19843275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341225000000005,
"min": 0.20741000000000004,
"max": 0.5812642,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.675709166666656e-05,
"min": 6.675709166666656e-05,
"max": 0.004921794225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002002712749999997,
"min": 0.0002002712749999997,
"max": 0.01406508358,
"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": "1719088405",
"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": "1719091069"
},
"total": 2664.044643061,
"count": 1,
"self": 0.4409343860002082,
"children": {
"run_training.setup": {
"total": 0.05776110499994047,
"count": 1,
"self": 0.05776110499994047
},
"TrainerController.start_learning": {
"total": 2663.54594757,
"count": 1,
"self": 4.634961178029698,
"children": {
"TrainerController._reset_env": {
"total": 2.9669836250000117,
"count": 1,
"self": 2.9669836250000117
},
"TrainerController.advance": {
"total": 2655.77011053397,
"count": 231718,
"self": 4.9176962818319225,
"children": {
"env_step": {
"total": 2026.1629531370827,
"count": 231718,
"self": 1657.5249507322283,
"children": {
"SubprocessEnvManager._take_step": {
"total": 365.56182719282685,
"count": 231718,
"self": 18.783081093777355,
"children": {
"TorchPolicy.evaluate": {
"total": 346.7787460990495,
"count": 222948,
"self": 346.7787460990495
}
}
},
"workers": {
"total": 3.0761752120275787,
"count": 231718,
"self": 0.0,
"children": {
"worker_root": {
"total": 2656.0486574969054,
"count": 231718,
"is_parallel": true,
"self": 1326.3849440519461,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009442099999432685,
"count": 1,
"is_parallel": true,
"self": 0.00023476499995922495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007094449999840435,
"count": 2,
"is_parallel": true,
"self": 0.0007094449999840435
}
}
},
"UnityEnvironment.step": {
"total": 0.030926850000014383,
"count": 1,
"is_parallel": true,
"self": 0.00042627999994238053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024039000004449917,
"count": 1,
"is_parallel": true,
"self": 0.00024039000004449917
},
"communicator.exchange": {
"total": 0.029375080000022535,
"count": 1,
"is_parallel": true,
"self": 0.029375080000022535
},
"steps_from_proto": {
"total": 0.000885100000004968,
"count": 1,
"is_parallel": true,
"self": 0.0002585969999699955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006265030000349725,
"count": 2,
"is_parallel": true,
"self": 0.0006265030000349725
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.6637134449593,
"count": 231717,
"is_parallel": true,
"self": 40.346010906041556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.41832081796167,
"count": 231717,
"is_parallel": true,
"self": 88.41832081796167
},
"communicator.exchange": {
"total": 1105.7228042250317,
"count": 231717,
"is_parallel": true,
"self": 1105.7228042250317
},
"steps_from_proto": {
"total": 95.17657749592433,
"count": 231717,
"is_parallel": true,
"self": 35.92902664181179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.247550854112546,
"count": 463434,
"is_parallel": true,
"self": 59.247550854112546
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.6894611150555,
"count": 231718,
"self": 6.981563565054785,
"children": {
"process_trajectory": {
"total": 164.5246955660009,
"count": 231718,
"self": 162.780781552,
"children": {
"RLTrainer._checkpoint": {
"total": 1.743914014000893,
"count": 10,
"self": 1.743914014000893
}
}
},
"_update_policy": {
"total": 453.18320198399977,
"count": 97,
"self": 360.3454847699936,
"children": {
"TorchPPOOptimizer.update": {
"total": 92.83771721400615,
"count": 3880,
"self": 92.83771721400615
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3050002962700091e-06,
"count": 1,
"self": 1.3050002962700091e-06
},
"TrainerController._save_models": {
"total": 0.17389092799976424,
"count": 1,
"self": 0.0034867700001086632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17040415799965558,
"count": 1,
"self": 0.17040415799965558
}
}
}
}
}
}
}