timflash's picture
First Push
32c50f8 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.29829519987106323,
"min": 0.29829519987106323,
"max": 1.4541839361190796,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9029.9921875,
"min": 8973.2353515625,
"max": 44114.125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989971.0,
"min": 29879.0,
"max": 989971.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989971.0,
"min": 29879.0,
"max": 989971.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.45593875646591187,
"min": -0.08875250071287155,
"max": 0.5358880758285522,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 119.4559555053711,
"min": -21.478105545043945,
"max": 148.9768829345703,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.037065111100673676,
"min": 0.0018073918763548136,
"max": 0.2894348204135895,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.7110595703125,
"min": 0.45727014541625977,
"max": 69.75379180908203,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06438473158515014,
"min": 0.06379926399799347,
"max": 0.07347701626536567,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9013862421921018,
"min": 0.5143391138575597,
"max": 1.0736490200438045,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013560336005624682,
"min": 0.001001737463756476,
"max": 0.015281688853528796,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18984470407874554,
"min": 0.013022587028834189,
"max": 0.21394364394940316,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.421433240507146e-06,
"min": 7.421433240507146e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010390006536710004,
"min": 0.00010390006536710004,
"max": 0.0035080181306606996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247377857142859,
"min": 0.10247377857142859,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4346329000000002,
"min": 1.3886848,
"max": 2.5693393000000007,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025713047928571436,
"min": 0.00025713047928571436,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003599826710000001,
"min": 0.003599826710000001,
"max": 0.11695699607,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007210309151560068,
"min": 0.007210309151560068,
"max": 0.49154549837112427,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10094432532787323,
"min": 0.10094432532787323,
"max": 3.4408185482025146,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 423.52777777777777,
"min": 355.3666666666667,
"max": 997.5625,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30494.0,
"min": 16806.0,
"max": 32834.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3819749766132898,
"min": -0.9359313033055514,
"max": 1.5789544128730326,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 99.50219831615686,
"min": -29.949801705777645,
"max": 138.0133984014392,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3819749766132898,
"min": -0.9359313033055514,
"max": 1.5789544128730326,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 99.50219831615686,
"min": -29.949801705777645,
"max": 138.0133984014392,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0318633267068233,
"min": 0.030334647247218526,
"max": 9.90843967567472,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.2941595228912774,
"min": 2.2679426462273113,
"max": 168.44347448647022,
"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": "1757772697",
"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",
"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": "1757774950"
},
"total": 2253.1393913699994,
"count": 1,
"self": 0.5356719399997019,
"children": {
"run_training.setup": {
"total": 0.022117135999906168,
"count": 1,
"self": 0.022117135999906168
},
"TrainerController.start_learning": {
"total": 2252.581602294,
"count": 1,
"self": 1.4464595719427962,
"children": {
"TrainerController._reset_env": {
"total": 2.65456518100018,
"count": 1,
"self": 2.65456518100018
},
"TrainerController.advance": {
"total": 2248.3819265350567,
"count": 63760,
"self": 1.4553881700426246,
"children": {
"env_step": {
"total": 1562.1060142520223,
"count": 63760,
"self": 1404.7994354219331,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.42045013004417,
"count": 63760,
"self": 4.968724371110966,
"children": {
"TorchPolicy.evaluate": {
"total": 151.4517257589332,
"count": 62547,
"self": 151.4517257589332
}
}
},
"workers": {
"total": 0.886128700044992,
"count": 63760,
"self": 0.0,
"children": {
"worker_root": {
"total": 2247.316131120034,
"count": 63760,
"is_parallel": true,
"self": 960.9083045870598,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018164349999096885,
"count": 1,
"is_parallel": true,
"self": 0.0005903210003452841,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012261139995644044,
"count": 8,
"is_parallel": true,
"self": 0.0012261139995644044
}
}
},
"UnityEnvironment.step": {
"total": 0.0920412679997753,
"count": 1,
"is_parallel": true,
"self": 0.0005030580000493501,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004439500003172725,
"count": 1,
"is_parallel": true,
"self": 0.0004439500003172725
},
"communicator.exchange": {
"total": 0.0895379129997309,
"count": 1,
"is_parallel": true,
"self": 0.0895379129997309
},
"steps_from_proto": {
"total": 0.0015563469996777712,
"count": 1,
"is_parallel": true,
"self": 0.0003513959995871119,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012049510000906594,
"count": 8,
"is_parallel": true,
"self": 0.0012049510000906594
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.407826532974,
"count": 63759,
"is_parallel": true,
"self": 33.25874259292095,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.427130779016352,
"count": 63759,
"is_parallel": true,
"self": 24.427130779016352
},
"communicator.exchange": {
"total": 1126.6848729060825,
"count": 63759,
"is_parallel": true,
"self": 1126.6848729060825
},
"steps_from_proto": {
"total": 102.03708025495416,
"count": 63759,
"is_parallel": true,
"self": 20.378891019257935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.65818923569623,
"count": 510072,
"is_parallel": true,
"self": 81.65818923569623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 684.8205241129917,
"count": 63760,
"self": 2.7024293510066855,
"children": {
"process_trajectory": {
"total": 130.2629124469895,
"count": 63760,
"self": 130.02357701398887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2393354330006332,
"count": 2,
"self": 0.2393354330006332
}
}
},
"_update_policy": {
"total": 551.8551823149955,
"count": 451,
"self": 308.95171002395864,
"children": {
"TorchPPOOptimizer.update": {
"total": 242.9034722910369,
"count": 22839,
"self": 242.9034722910369
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5780005924170837e-06,
"count": 1,
"self": 1.5780005924170837e-06
},
"TrainerController._save_models": {
"total": 0.09864942799958953,
"count": 1,
"self": 0.0012615859996003564,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09738784199998918,
"count": 1,
"self": 0.09738784199998918
}
}
}
}
}
}
}