ppo-Pyramids / run_logs /timers.json
madmage's picture
First Push
aecb807 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3412911891937256,
"min": 0.3412911891937256,
"max": 1.3773759603500366,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10309.724609375,
"min": 10309.724609375,
"max": 41784.078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989949.0,
"min": 29946.0,
"max": 989949.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989949.0,
"min": 29946.0,
"max": 989949.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6503241062164307,
"min": -0.09854932874441147,
"max": 0.6574900150299072,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 187.29335021972656,
"min": -23.651838302612305,
"max": 187.29335021972656,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.033630210906267166,
"min": -0.009578624740242958,
"max": 0.5224274396896362,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.685501098632812,
"min": -2.5479142665863037,
"max": 123.8153076171875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0678089177064762,
"min": 0.06647915366435579,
"max": 0.07239087736488965,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9493248478906667,
"min": 0.5355891522318167,
"max": 1.0858631604733449,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01595217076571905,
"min": 0.000502209706729219,
"max": 0.016707899820420525,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2233303907200667,
"min": 0.006026516480750628,
"max": 0.23391059748588733,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.476890364878573e-06,
"min": 7.476890364878573e-06,
"max": 0.000295014226661925,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010467646510830002,
"min": 0.00010467646510830002,
"max": 0.0035107649297451,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024922642857143,
"min": 0.1024922642857143,
"max": 0.198338075,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4348917,
"min": 1.4348917,
"max": 2.6173900000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025897720214285716,
"min": 0.00025897720214285716,
"max": 0.0098339736925,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036256808300000006,
"min": 0.0036256808300000006,
"max": 0.11704846451,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014543937519192696,
"min": 0.014543937519192696,
"max": 0.5522206425666809,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20361512899398804,
"min": 0.20361512899398804,
"max": 4.417765140533447,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 290.1923076923077,
"min": 287.3495145631068,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30180.0,
"min": 16873.0,
"max": 32362.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6705242551646187,
"min": -0.9999625524505973,
"max": 1.6906329935904845,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 172.06399828195572,
"min": -31.998801678419113,
"max": 174.1351983398199,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6705242551646187,
"min": -0.9999625524505973,
"max": 1.6906329935904845,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 172.06399828195572,
"min": -31.998801678419113,
"max": 174.1351983398199,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.043595597102873036,
"min": 0.043595597102873036,
"max": 10.707304498728584,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.490346501595923,
"min": 4.490346501595923,
"max": 182.02417647838593,
"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": "1756130946",
"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-mine.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": "1756133508"
},
"total": 2561.832042149,
"count": 1,
"self": 0.9178295559995604,
"children": {
"run_training.setup": {
"total": 0.0236931890001415,
"count": 1,
"self": 0.0236931890001415
},
"TrainerController.start_learning": {
"total": 2560.890519404,
"count": 1,
"self": 1.6563844299794255,
"children": {
"TrainerController._reset_env": {
"total": 3.4476968799999668,
"count": 1,
"self": 3.4476968799999668
},
"TrainerController.advance": {
"total": 2555.66581584902,
"count": 64282,
"self": 1.7810580060559005,
"children": {
"env_step": {
"total": 1851.793785284978,
"count": 64282,
"self": 1679.1094486209793,
"children": {
"SubprocessEnvManager._take_step": {
"total": 171.64247267697397,
"count": 64282,
"self": 5.13843552399112,
"children": {
"TorchPolicy.evaluate": {
"total": 166.50403715298285,
"count": 62563,
"self": 166.50403715298285
}
}
},
"workers": {
"total": 1.0418639870247262,
"count": 64282,
"self": 0.0,
"children": {
"worker_root": {
"total": 2554.1411865749687,
"count": 64282,
"is_parallel": true,
"self": 1006.8602931529281,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006219339999915974,
"count": 1,
"is_parallel": true,
"self": 0.004890756999429868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013285830004861054,
"count": 8,
"is_parallel": true,
"self": 0.0013285830004861054
}
}
},
"UnityEnvironment.step": {
"total": 0.058590438999999606,
"count": 1,
"is_parallel": true,
"self": 0.000647670999796901,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005238020000888355,
"count": 1,
"is_parallel": true,
"self": 0.0005238020000888355
},
"communicator.exchange": {
"total": 0.0556566230000044,
"count": 1,
"is_parallel": true,
"self": 0.0556566230000044
},
"steps_from_proto": {
"total": 0.0017623430001094675,
"count": 1,
"is_parallel": true,
"self": 0.00038244300048972946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001379899999619738,
"count": 8,
"is_parallel": true,
"self": 0.001379899999619738
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1547.2808934220407,
"count": 64281,
"is_parallel": true,
"self": 36.48119159606881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.962642434998543,
"count": 64281,
"is_parallel": true,
"self": 23.962642434998543
},
"communicator.exchange": {
"total": 1384.7269593399792,
"count": 64281,
"is_parallel": true,
"self": 1384.7269593399792
},
"steps_from_proto": {
"total": 102.1101000509941,
"count": 64281,
"is_parallel": true,
"self": 21.064782964836695,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.04531708615741,
"count": 514248,
"is_parallel": true,
"self": 81.04531708615741
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 702.0909725579859,
"count": 64282,
"self": 3.4675447910037747,
"children": {
"process_trajectory": {
"total": 131.30748037298054,
"count": 64282,
"self": 130.96885652998026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3386238430002777,
"count": 2,
"self": 0.3386238430002777
}
}
},
"_update_policy": {
"total": 567.3159473940016,
"count": 458,
"self": 312.9695931520075,
"children": {
"TorchPPOOptimizer.update": {
"total": 254.34635424199405,
"count": 22839,
"self": 254.34635424199405
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1320003068249207e-06,
"count": 1,
"self": 1.1320003068249207e-06
},
"TrainerController._save_models": {
"total": 0.12062111300019751,
"count": 1,
"self": 0.0017953990004571097,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1188257139997404,
"count": 1,
"self": 0.1188257139997404
}
}
}
}
}
}
}