ppo-Pyramids / run_logs /timers.json
Neronuser's picture
First Push
2dab868
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.651121199131012,
"min": 0.622680127620697,
"max": 1.5300097465515137,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 19679.486328125,
"min": 18760.107421875,
"max": 46414.375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989966.0,
"min": 29952.0,
"max": 989966.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989966.0,
"min": 29952.0,
"max": 989966.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.39598867297172546,
"min": -0.17632055282592773,
"max": 0.47539058327674866,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 104.93699645996094,
"min": -41.78797149658203,
"max": 130.25701904296875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -3.155487060546875,
"min": -3.155487060546875,
"max": 0.6024162173271179,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -836.2041015625,
"min": -836.2041015625,
"max": 160.24270629882812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06559237373723936,
"min": 0.06487247922978852,
"max": 0.07436989429909108,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9182932323213511,
"min": 0.5142035034238281,
"max": 1.0478927819086832,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 1.1456383212713435,
"min": 0.00017560694777335104,
"max": 1.1456383212713435,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 16.038936497798808,
"min": 0.0017560694777335104,
"max": 16.038936497798808,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.451047516350002e-06,
"min": 7.451047516350002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010431466522890003,
"min": 0.00010431466522890003,
"max": 0.0031386344537886,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248365,
"min": 0.10248365,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4347710999999999,
"min": 1.3886848,
"max": 2.3462114000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002581166350000001,
"min": 0.0002581166350000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003613632890000001,
"min": 0.003613632890000001,
"max": 0.10464651886,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008649734780192375,
"min": 0.008649734780192375,
"max": 0.3485957682132721,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12109629064798355,
"min": 0.12109629064798355,
"max": 2.4401702880859375,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 447.8888888888889,
"min": 379.725,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28217.0,
"min": 15984.0,
"max": 32521.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4568380731202306,
"min": -1.0000000521540642,
"max": 1.5611492309774926,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 91.78079860657454,
"min": -31.999601677060127,
"max": 123.61999838799238,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4568380731202306,
"min": -1.0000000521540642,
"max": 1.5611492309774926,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 91.78079860657454,
"min": -31.999601677060127,
"max": 123.61999838799238,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04073006372911752,
"min": 0.03513740330699875,
"max": 7.198170633986592,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.565994014934404,
"min": 2.565994014934404,
"max": 115.17073014378548,
"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": "1684146392",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684148505"
},
"total": 2112.7357567130002,
"count": 1,
"self": 0.42345435600009296,
"children": {
"run_training.setup": {
"total": 0.05903338000007352,
"count": 1,
"self": 0.05903338000007352
},
"TrainerController.start_learning": {
"total": 2112.253268977,
"count": 1,
"self": 1.3784566970316519,
"children": {
"TrainerController._reset_env": {
"total": 4.840437105000092,
"count": 1,
"self": 4.840437105000092
},
"TrainerController.advance": {
"total": 2105.945014780968,
"count": 63495,
"self": 1.3289549990645355,
"children": {
"env_step": {
"total": 1483.9190226799778,
"count": 63495,
"self": 1375.5041232589142,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.61153857407021,
"count": 63495,
"self": 4.757940157080839,
"children": {
"TorchPolicy.evaluate": {
"total": 102.85359841698937,
"count": 62553,
"self": 102.85359841698937
}
}
},
"workers": {
"total": 0.8033608469934279,
"count": 63495,
"self": 0.0,
"children": {
"worker_root": {
"total": 2107.4490531339557,
"count": 63495,
"is_parallel": true,
"self": 844.367814473916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002524802000152704,
"count": 1,
"is_parallel": true,
"self": 0.0007311260003461939,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00179367599980651,
"count": 8,
"is_parallel": true,
"self": 0.00179367599980651
}
}
},
"UnityEnvironment.step": {
"total": 0.048067272000025696,
"count": 1,
"is_parallel": true,
"self": 0.0005665949997819553,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005250060000889789,
"count": 1,
"is_parallel": true,
"self": 0.0005250060000889789
},
"communicator.exchange": {
"total": 0.04502351000019189,
"count": 1,
"is_parallel": true,
"self": 0.04502351000019189
},
"steps_from_proto": {
"total": 0.0019521609999628708,
"count": 1,
"is_parallel": true,
"self": 0.00048609699979351717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014660640001693537,
"count": 8,
"is_parallel": true,
"self": 0.0014660640001693537
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.0812386600396,
"count": 63494,
"is_parallel": true,
"self": 31.27361648507099,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.487637775971507,
"count": 63494,
"is_parallel": true,
"self": 23.487637775971507
},
"communicator.exchange": {
"total": 1108.003561470023,
"count": 63494,
"is_parallel": true,
"self": 1108.003561470023
},
"steps_from_proto": {
"total": 100.31642292897413,
"count": 63494,
"is_parallel": true,
"self": 20.68477694389344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.6316459850807,
"count": 507952,
"is_parallel": true,
"self": 79.6316459850807
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 620.6970371019258,
"count": 63495,
"self": 2.3877666429709734,
"children": {
"process_trajectory": {
"total": 106.60703081295264,
"count": 63495,
"self": 106.3976857019527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2093451109999478,
"count": 2,
"self": 0.2093451109999478
}
}
},
"_update_policy": {
"total": 511.7022396460022,
"count": 433,
"self": 329.9131216379967,
"children": {
"TorchPPOOptimizer.update": {
"total": 181.78911800800552,
"count": 22809,
"self": 181.78911800800552
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0930002645181958e-06,
"count": 1,
"self": 1.0930002645181958e-06
},
"TrainerController._save_models": {
"total": 0.08935930100005862,
"count": 1,
"self": 0.0013581440002781164,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0880011569997805,
"count": 1,
"self": 0.0880011569997805
}
}
}
}
}
}
}