rl-Pyramids1 / run_logs /timers.json
FranEnguix's picture
First Push
92424f9
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.11904668062925339,
"min": 0.11854852735996246,
"max": 1.4648370742797852,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3569.49560546875,
"min": 3567.83642578125,
"max": 44437.296875,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999925.0,
"min": 29923.0,
"max": 2999925.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999925.0,
"min": 29923.0,
"max": 2999925.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.855981171131134,
"min": -0.13573695719242096,
"max": 0.9029719829559326,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 261.93023681640625,
"min": -32.57686996459961,
"max": 286.24212646484375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.020232953131198883,
"min": -0.007196659687906504,
"max": 0.3321530818939209,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.191283702850342,
"min": -2.0942280292510986,
"max": 78.72028350830078,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0661955536897516,
"min": 0.06527114040282968,
"max": 0.07674130434250438,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9267377516565224,
"min": 0.4991760464741758,
"max": 1.0743782607950614,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014059786943280847,
"min": 0.0011896181640310489,
"max": 0.01812642000316243,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19683701720593186,
"min": 0.014275417968372586,
"max": 0.25376988004427403,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4229995256999985e-06,
"min": 1.4229995256999985e-06,
"max": 0.0002984113862438238,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.992199335979998e-05,
"min": 1.992199335979998e-05,
"max": 0.004072459242513633,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10047430000000002,
"min": 0.10047430000000002,
"max": 0.19947046190476195,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4066402000000002,
"min": 1.3962932333333335,
"max": 2.857486366666666,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.7382569999999966e-05,
"min": 5.7382569999999966e-05,
"max": 0.009947099144285713,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008033559799999995,
"min": 0.0008033559799999995,
"max": 0.13576288802999997,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01838000677525997,
"min": 0.016804298385977745,
"max": 0.5083096623420715,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2573201060295105,
"min": 0.23526018857955933,
"max": 3.5581676959991455,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 213.61870503597123,
"min": 187.29605263157896,
"max": 997.2666666666667,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29693.0,
"min": 16722.0,
"max": 33265.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7728941877898963,
"min": -0.9315533851583798,
"max": 1.8118807836281543,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 244.65939791500568,
"min": -30.736001655459404,
"max": 287.1199979484081,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7728941877898963,
"min": -0.9315533851583798,
"max": 1.8118807836281543,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 244.65939791500568,
"min": -30.736001655459404,
"max": 287.1199979484081,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03983358411420815,
"min": 0.034012592773185274,
"max": 9.525116497979445,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.497034607760725,
"min": 4.84589851659257,
"max": 161.92698046565056,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680899796",
"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": "1680907315"
},
"total": 7519.459821255001,
"count": 1,
"self": 0.48222539700145717,
"children": {
"run_training.setup": {
"total": 0.10892754600013177,
"count": 1,
"self": 0.10892754600013177
},
"TrainerController.start_learning": {
"total": 7518.8686683119995,
"count": 1,
"self": 4.536888536273182,
"children": {
"TrainerController._reset_env": {
"total": 4.27148929100008,
"count": 1,
"self": 4.27148929100008
},
"TrainerController.advance": {
"total": 7509.966673717728,
"count": 195861,
"self": 4.8171705228269275,
"children": {
"env_step": {
"total": 5691.1699927449645,
"count": 195861,
"self": 5358.275055846609,
"children": {
"SubprocessEnvManager._take_step": {
"total": 330.22657506226005,
"count": 195861,
"self": 14.815799771296724,
"children": {
"TorchPolicy.evaluate": {
"total": 315.41077529096333,
"count": 187564,
"self": 315.41077529096333
}
}
},
"workers": {
"total": 2.6683618360959827,
"count": 195861,
"self": 0.0,
"children": {
"worker_root": {
"total": 7501.36142092792,
"count": 195861,
"is_parallel": true,
"self": 2501.407053167859,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017689130002054299,
"count": 1,
"is_parallel": true,
"self": 0.0006476930000189896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011212200001864403,
"count": 8,
"is_parallel": true,
"self": 0.0011212200001864403
}
}
},
"UnityEnvironment.step": {
"total": 0.07430531499994686,
"count": 1,
"is_parallel": true,
"self": 0.0007283019999704266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005165290001514222,
"count": 1,
"is_parallel": true,
"self": 0.0005165290001514222
},
"communicator.exchange": {
"total": 0.07148498299989114,
"count": 1,
"is_parallel": true,
"self": 0.07148498299989114
},
"steps_from_proto": {
"total": 0.0015755009999338654,
"count": 1,
"is_parallel": true,
"self": 0.0003450009999141912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012305000000196742,
"count": 8,
"is_parallel": true,
"self": 0.0012305000000196742
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4999.954367760061,
"count": 195860,
"is_parallel": true,
"self": 98.50989354934427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.58159588182548,
"count": 195860,
"is_parallel": true,
"self": 74.58159588182548
},
"communicator.exchange": {
"total": 4527.607925359053,
"count": 195860,
"is_parallel": true,
"self": 4527.607925359053
},
"steps_from_proto": {
"total": 299.2549529698381,
"count": 195860,
"is_parallel": true,
"self": 65.95915262216704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 233.29580034767105,
"count": 1566880,
"is_parallel": true,
"self": 233.29580034767105
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1813.9795104499365,
"count": 195861,
"self": 8.865567593038122,
"children": {
"process_trajectory": {
"total": 338.6935061619008,
"count": 195861,
"self": 337.96020419490173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.733301966999079,
"count": 6,
"self": 0.733301966999079
}
}
},
"_update_policy": {
"total": 1466.4204366949975,
"count": 1402,
"self": 929.950787631092,
"children": {
"TorchPPOOptimizer.update": {
"total": 536.4696490639055,
"count": 68382,
"self": 536.4696490639055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.549985406920314e-07,
"count": 1,
"self": 9.549985406920314e-07
},
"TrainerController._save_models": {
"total": 0.09361581200028013,
"count": 1,
"self": 0.0014196279989846516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09219618400129548,
"count": 1,
"self": 0.09219618400129548
}
}
}
}
}
}
}