ppo-PyramidsRND / run_logs /timers.json
pinaggle's picture
First Push
8111636
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3049434423446655,
"min": 0.3015599846839905,
"max": 1.49657142162323,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9094.6328125,
"min": 9094.6328125,
"max": 45399.9921875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5238995552062988,
"min": -0.10958795994520187,
"max": 0.5409738421440125,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 146.16796875,
"min": -25.972347259521484,
"max": 147.91700744628906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015654493123292923,
"min": -0.01609540730714798,
"max": 0.1750977635383606,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.367603778839111,
"min": -3.8146114349365234,
"max": 42.19856262207031,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06678700949095061,
"min": 0.0656532234772655,
"max": 0.07360521700213205,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9350181328733085,
"min": 0.49968936517881496,
"max": 1.0635433118555275,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01418495521731417,
"min": 0.0011120914449797281,
"max": 0.014956410998517338,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19858937304239838,
"min": 0.013345097339756739,
"max": 0.20938975397924273,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.43034752325e-06,
"min": 7.43034752325e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001040248653255,
"min": 0.0001040248653255,
"max": 0.0035080253306583,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247675,
"min": 0.10247675,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4346745,
"min": 1.3886848,
"max": 2.5693417000000007,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257427325,
"min": 0.000257427325,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036039825500000003,
"min": 0.0036039825500000003,
"max": 0.11695723583,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01106763444840908,
"min": 0.01106763444840908,
"max": 0.37688490748405457,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15494687855243683,
"min": 0.15494687855243683,
"max": 2.6381943225860596,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 348.3953488372093,
"min": 348.3953488372093,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29962.0,
"min": 15984.0,
"max": 33376.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6050744041973768,
"min": -1.0000000521540642,
"max": 1.6050744041973768,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 138.0363987609744,
"min": -29.408001750707626,
"max": 138.0363987609744,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6050744041973768,
"min": -1.0000000521540642,
"max": 1.6050744041973768,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 138.0363987609744,
"min": -29.408001750707626,
"max": 138.0363987609744,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04049955076385062,
"min": 0.04049955076385062,
"max": 7.47456144541502,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4829613656911533,
"min": 3.1061000449117273,
"max": 119.59298312664032,
"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": "1681311596",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1681313662"
},
"total": 2065.736983595,
"count": 1,
"self": 0.490990793000492,
"children": {
"run_training.setup": {
"total": 0.11353841999971337,
"count": 1,
"self": 0.11353841999971337
},
"TrainerController.start_learning": {
"total": 2065.1324543819997,
"count": 1,
"self": 1.3625132259908241,
"children": {
"TrainerController._reset_env": {
"total": 3.712635296999906,
"count": 1,
"self": 3.712635296999906
},
"TrainerController.advance": {
"total": 2059.967248600009,
"count": 63881,
"self": 1.3930522237710647,
"children": {
"env_step": {
"total": 1468.9918440901115,
"count": 63881,
"self": 1367.3313024070362,
"children": {
"SubprocessEnvManager._take_step": {
"total": 100.86627525204312,
"count": 63881,
"self": 4.511377967107364,
"children": {
"TorchPolicy.evaluate": {
"total": 96.35489728493576,
"count": 62557,
"self": 96.35489728493576
}
}
},
"workers": {
"total": 0.7942664310321561,
"count": 63881,
"self": 0.0,
"children": {
"worker_root": {
"total": 2060.55264572605,
"count": 63881,
"is_parallel": true,
"self": 800.4967278741019,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016432970001005742,
"count": 1,
"is_parallel": true,
"self": 0.0005349010002646537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011083959998359205,
"count": 8,
"is_parallel": true,
"self": 0.0011083959998359205
}
}
},
"UnityEnvironment.step": {
"total": 0.04826943799980654,
"count": 1,
"is_parallel": true,
"self": 0.000509986999531975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004562359999908949,
"count": 1,
"is_parallel": true,
"self": 0.0004562359999908949
},
"communicator.exchange": {
"total": 0.04568632100017567,
"count": 1,
"is_parallel": true,
"self": 0.04568632100017567
},
"steps_from_proto": {
"total": 0.0016168940001080045,
"count": 1,
"is_parallel": true,
"self": 0.00040791200035528163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001208981999752723,
"count": 8,
"is_parallel": true,
"self": 0.001208981999752723
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.055917851948,
"count": 63880,
"is_parallel": true,
"self": 31.317731464015196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.004285825934858,
"count": 63880,
"is_parallel": true,
"self": 22.004285825934858
},
"communicator.exchange": {
"total": 1116.1445619818978,
"count": 63880,
"is_parallel": true,
"self": 1116.1445619818978
},
"steps_from_proto": {
"total": 90.58933858010005,
"count": 63880,
"is_parallel": true,
"self": 19.044374277832958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.54496430226709,
"count": 511040,
"is_parallel": true,
"self": 71.54496430226709
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 589.5823522861265,
"count": 63881,
"self": 2.411564842163898,
"children": {
"process_trajectory": {
"total": 101.96705783794869,
"count": 63881,
"self": 101.76656657694866,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20049126100002468,
"count": 2,
"self": 0.20049126100002468
}
}
},
"_update_policy": {
"total": 485.2037296060139,
"count": 451,
"self": 309.00413804300615,
"children": {
"TorchPPOOptimizer.update": {
"total": 176.19959156300774,
"count": 22827,
"self": 176.19959156300774
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0350004231440835e-06,
"count": 1,
"self": 1.0350004231440835e-06
},
"TrainerController._save_models": {
"total": 0.09005622399945423,
"count": 1,
"self": 0.0013578959988080896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08869832800064614,
"count": 1,
"self": 0.08869832800064614
}
}
}
}
}
}
}