ppo-Pyramids / run_logs /timers.json
dil-gregkowalski's picture
First Push
2cbedbe
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5445341467857361,
"min": 0.4771881699562073,
"max": 1.3809013366699219,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16318.599609375,
"min": 14292.740234375,
"max": 41891.0234375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.2832023799419403,
"min": -0.10329709202051163,
"max": 0.2954742908477783,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 72.78301239013672,
"min": -24.89459991455078,
"max": 77.11878967285156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.3229178488254547,
"min": -0.07652556151151657,
"max": 0.6601830124855042,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 82.98988342285156,
"min": -19.058780670166016,
"max": 156.46337890625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07007959838309842,
"min": 0.06570602781305622,
"max": 0.07301157767857626,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0511939757464763,
"min": 0.47657626148044996,
"max": 1.067806505486563,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.021230292000756084,
"min": 6.210688162809462e-05,
"max": 0.024106550269701658,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.31845438001134124,
"min": 0.0008694963427933246,
"max": 0.3374917037758232,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.462377512573329e-06,
"min": 7.462377512573329e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011193566268859994,
"min": 0.00011193566268859994,
"max": 0.0032236945254351993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248742666666667,
"min": 0.10248742666666667,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373114,
"min": 1.3691136000000002,
"max": 2.3468857,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025849392399999993,
"min": 0.00025849392399999993,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003877408859999999,
"min": 0.003877408859999999,
"max": 0.10746902352,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014764961786568165,
"min": 0.014764961786568165,
"max": 0.641866147518158,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22147442400455475,
"min": 0.21127602458000183,
"max": 4.493062973022461,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 565.54,
"min": 507.38709677419354,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28277.0,
"min": 15984.0,
"max": 32584.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.11975996658206,
"min": -1.0000000521540642,
"max": 1.2274163686594024,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 55.98799832910299,
"min": -32.000001668930054,
"max": 74.87239848822355,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.11975996658206,
"min": -1.0000000521540642,
"max": 1.2274163686594024,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 55.98799832910299,
"min": -32.000001668930054,
"max": 74.87239848822355,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08548102094558999,
"min": 0.07958300245141411,
"max": 14.193683192133904,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.2740510472794995,
"min": 4.2740510472794995,
"max": 227.09893107414246,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1704262375",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704264614"
},
"total": 2238.9942004880004,
"count": 1,
"self": 1.0493822360003833,
"children": {
"run_training.setup": {
"total": 0.05089480500009813,
"count": 1,
"self": 0.05089480500009813
},
"TrainerController.start_learning": {
"total": 2237.893923447,
"count": 1,
"self": 1.6252647600376804,
"children": {
"TrainerController._reset_env": {
"total": 2.0597108280001066,
"count": 1,
"self": 2.0597108280001066
},
"TrainerController.advance": {
"total": 2234.0756149579624,
"count": 63317,
"self": 1.6648795799660547,
"children": {
"env_step": {
"total": 1585.7555316279122,
"count": 63317,
"self": 1439.0327987428875,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.70437627999218,
"count": 63317,
"self": 5.203733065990036,
"children": {
"TorchPolicy.evaluate": {
"total": 140.50064321400214,
"count": 62571,
"self": 140.50064321400214
}
}
},
"workers": {
"total": 1.0183566050325226,
"count": 63317,
"self": 0.0,
"children": {
"worker_root": {
"total": 2232.019791868073,
"count": 63317,
"is_parallel": true,
"self": 925.9639112361926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017849819998900784,
"count": 1,
"is_parallel": true,
"self": 0.000617542999862053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011674390000280255,
"count": 8,
"is_parallel": true,
"self": 0.0011674390000280255
}
}
},
"UnityEnvironment.step": {
"total": 0.04900497800008452,
"count": 1,
"is_parallel": true,
"self": 0.0006576090001999546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004758969998874818,
"count": 1,
"is_parallel": true,
"self": 0.0004758969998874818
},
"communicator.exchange": {
"total": 0.046142088000124204,
"count": 1,
"is_parallel": true,
"self": 0.046142088000124204
},
"steps_from_proto": {
"total": 0.00172938399987288,
"count": 1,
"is_parallel": true,
"self": 0.0003671419997317571,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013622420001411228,
"count": 8,
"is_parallel": true,
"self": 0.0013622420001411228
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1306.0558806318802,
"count": 63316,
"is_parallel": true,
"self": 36.72895644892765,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.24320409400525,
"count": 63316,
"is_parallel": true,
"self": 26.24320409400525
},
"communicator.exchange": {
"total": 1135.493209012968,
"count": 63316,
"is_parallel": true,
"self": 1135.493209012968
},
"steps_from_proto": {
"total": 107.5905110759793,
"count": 63316,
"is_parallel": true,
"self": 22.48535522587622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.10515585010307,
"count": 506528,
"is_parallel": true,
"self": 85.10515585010307
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 646.6552037500844,
"count": 63317,
"self": 2.957320897057798,
"children": {
"process_trajectory": {
"total": 131.57003781203161,
"count": 63317,
"self": 131.32120400203144,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24883381000017835,
"count": 2,
"self": 0.24883381000017835
}
}
},
"_update_policy": {
"total": 512.127845040995,
"count": 436,
"self": 304.03438685897913,
"children": {
"TorchPPOOptimizer.update": {
"total": 208.09345818201587,
"count": 22833,
"self": 208.09345818201587
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2419995982781984e-06,
"count": 1,
"self": 1.2419995982781984e-06
},
"TrainerController._save_models": {
"total": 0.13333165899985033,
"count": 1,
"self": 0.0023600270005772472,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13097163199927309,
"count": 1,
"self": 0.13097163199927309
}
}
}
}
}
}
}