ppo-Pyramids / run_logs /timers.json
AlaaWO's picture
First Push
04a61d7 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6916652917861938,
"min": 0.6916652917861938,
"max": 1.4080395698547363,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 21015.55859375,
"min": 21015.55859375,
"max": 42714.2890625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989905.0,
"min": 29952.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989905.0,
"min": 29952.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.10776599496603012,
"min": -0.11782751977443695,
"max": 0.20177793502807617,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 26.83373260498047,
"min": -28.396432876586914,
"max": 52.05870819091797,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.37718653678894043,
"min": -0.027455344796180725,
"max": 0.45064014196395874,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 93.91944885253906,
"min": -6.973657608032227,
"max": 110.39928436279297,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06622074532761615,
"min": 0.06311402284297786,
"max": 0.07521457803940743,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9933111799142422,
"min": 0.5134917922621063,
"max": 1.0576979669094015,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.05547178800303787,
"min": 0.00014228067045596852,
"max": 0.05547178800303787,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.832076820045568,
"min": 0.0018496487159275908,
"max": 0.832076820045568,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.548737483786667e-06,
"min": 7.548737483786667e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011323106225680002,
"min": 0.00011323106225680002,
"max": 0.0033775879741373997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251621333333334,
"min": 0.10251621333333334,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5377432000000002,
"min": 1.3886848,
"max": 2.4258626,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000261369712,
"min": 0.000261369712,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00392054568,
"min": 0.00392054568,
"max": 0.11260367374,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011246404610574245,
"min": 0.011246404610574245,
"max": 0.4392682611942291,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1686960756778717,
"min": 0.16218088567256927,
"max": 3.0748777389526367,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 751.5128205128206,
"min": 623.2439024390244,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29309.0,
"min": 15984.0,
"max": 33433.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.42772303846402043,
"min": -1.0000000521540642,
"max": 0.8888194788156486,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 16.681198500096798,
"min": -31.998001664876938,
"max": 40.535198375582695,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.42772303846402043,
"min": -1.0000000521540642,
"max": 0.8888194788156486,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 16.681198500096798,
"min": -31.998001664876938,
"max": 40.535198375582695,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08730586382667892,
"min": 0.07607401536401123,
"max": 8.762014825828373,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.404928689240478,
"min": 3.404928689240478,
"max": 140.19223721325397,
"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": "1767685250",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767687434"
},
"total": 2183.892894319,
"count": 1,
"self": 0.47730189399953815,
"children": {
"run_training.setup": {
"total": 0.02409901800001535,
"count": 1,
"self": 0.02409901800001535
},
"TrainerController.start_learning": {
"total": 2183.3914934070003,
"count": 1,
"self": 1.293333436055491,
"children": {
"TrainerController._reset_env": {
"total": 2.12317791199996,
"count": 1,
"self": 2.12317791199996
},
"TrainerController.advance": {
"total": 2179.892669545945,
"count": 63236,
"self": 1.4219942258996525,
"children": {
"env_step": {
"total": 1513.5479317990469,
"count": 63236,
"self": 1361.7156906000537,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.04040571898543,
"count": 63236,
"self": 4.655760033960746,
"children": {
"TorchPolicy.evaluate": {
"total": 146.38464568502468,
"count": 62581,
"self": 146.38464568502468
}
}
},
"workers": {
"total": 0.7918354800076486,
"count": 63236,
"self": 0.0,
"children": {
"worker_root": {
"total": 2176.731468397018,
"count": 63236,
"is_parallel": true,
"self": 932.0167616310532,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020137669999940044,
"count": 1,
"is_parallel": true,
"self": 0.0006162290000020221,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013975379999919824,
"count": 8,
"is_parallel": true,
"self": 0.0013975379999919824
}
}
},
"UnityEnvironment.step": {
"total": 0.05016803199998776,
"count": 1,
"is_parallel": true,
"self": 0.0005811390000189931,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000491498999963369,
"count": 1,
"is_parallel": true,
"self": 0.000491498999963369
},
"communicator.exchange": {
"total": 0.04736882899999273,
"count": 1,
"is_parallel": true,
"self": 0.04736882899999273
},
"steps_from_proto": {
"total": 0.0017265650000126698,
"count": 1,
"is_parallel": true,
"self": 0.0003277550000575502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013988099999551196,
"count": 8,
"is_parallel": true,
"self": 0.0013988099999551196
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1244.7147067659648,
"count": 63235,
"is_parallel": true,
"self": 33.77443699891728,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.42054946202859,
"count": 63235,
"is_parallel": true,
"self": 23.42054946202859
},
"communicator.exchange": {
"total": 1078.979779210979,
"count": 63235,
"is_parallel": true,
"self": 1078.979779210979
},
"steps_from_proto": {
"total": 108.53994109404005,
"count": 63235,
"is_parallel": true,
"self": 22.68346775397356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.85647334006649,
"count": 505880,
"is_parallel": true,
"self": 85.85647334006649
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.9227435209984,
"count": 63236,
"self": 2.4608509189855567,
"children": {
"process_trajectory": {
"total": 122.85939064701233,
"count": 63236,
"self": 122.5633931970126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29599744999973154,
"count": 2,
"self": 0.29599744999973154
}
}
},
"_update_policy": {
"total": 539.6025019550005,
"count": 441,
"self": 301.64083516496066,
"children": {
"TorchPPOOptimizer.update": {
"total": 237.96166679003989,
"count": 22782,
"self": 237.96166679003989
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.08231148499999108,
"count": 1,
"self": 0.0009595859996807121,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08135189900031037,
"count": 1,
"self": 0.08135189900031037
}
}
}
}
}
}
}