poca-SoccerTwos / run_logs /timers.json
jannikskytt's picture
First Push`
0cccf2d
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5304807424545288,
"min": 1.4965088367462158,
"max": 3.2958123683929443,
"count": 600
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 31148.34375,
"min": 23634.31640625,
"max": 113124.328125,
"count": 600
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 58.59036144578313,
"min": 43.5625,
"max": 999.0,
"count": 600
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19452.0,
"min": 11480.0,
"max": 30740.0,
"count": 600
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1548.6887301926909,
"min": 1193.6326306897918,
"max": 1558.9435496776152,
"count": 592
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 257082.32921198668,
"min": 2391.923115635179,
"max": 342217.4303449959,
"count": 592
},
"SoccerTwos.Step.mean": {
"value": 5999978.0,
"min": 9386.0,
"max": 5999978.0,
"count": 600
},
"SoccerTwos.Step.sum": {
"value": 5999978.0,
"min": 9386.0,
"max": 5999978.0,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0074770813807845116,
"min": -0.10001322627067566,
"max": 0.1820773333311081,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.2337183952331543,
"min": -14.401905059814453,
"max": 24.064876556396484,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.011652871035039425,
"min": -0.10207614302635193,
"max": 0.1816205084323883,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.922723650932312,
"min": -14.915702819824219,
"max": 24.292831420898438,
"count": 600
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 600
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.1296048475034309,
"min": -0.5449058816713446,
"max": 0.48300656090017224,
"count": 600
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 21.3847998380661,
"min": -40.061400055885315,
"max": 56.67460000514984,
"count": 600
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.1296048475034309,
"min": -0.5449058816713446,
"max": 0.48300656090017224,
"count": 600
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 21.3847998380661,
"min": -40.061400055885315,
"max": 56.67460000514984,
"count": 600
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 600
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 600
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017827743666712196,
"min": 0.01392420891963411,
"max": 0.02500892789568752,
"count": 289
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.017827743666712196,
"min": 0.01392420891963411,
"max": 0.02500892789568752,
"count": 289
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0859621961414814,
"min": 1.3543370896513806e-05,
"max": 0.106248509734869,
"count": 289
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0859621961414814,
"min": 1.3543370896513806e-05,
"max": 0.106248509734869,
"count": 289
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09397193983197212,
"min": 1.4827599607087904e-05,
"max": 0.11614800736308098,
"count": 289
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09397193983197212,
"min": 1.4827599607087904e-05,
"max": 0.11614800736308098,
"count": 289
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 289
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 289
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 289
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 289
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 289
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 289
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675865071",
"python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\jasp\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.1+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1675899430"
},
"total": 34358.701182699995,
"count": 1,
"self": 1.0405286999884993,
"children": {
"run_training.setup": {
"total": 0.39365250000000174,
"count": 1,
"self": 0.39365250000000174
},
"TrainerController.start_learning": {
"total": 34357.267001500004,
"count": 1,
"self": 12.031285398981709,
"children": {
"TrainerController._reset_env": {
"total": 95.56169679999712,
"count": 20,
"self": 95.56169679999712
},
"TrainerController.advance": {
"total": 34249.48391550103,
"count": 409917,
"self": 12.49532350168738,
"children": {
"env_step": {
"total": 9563.38375319893,
"count": 409917,
"self": 7260.532176796392,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2294.9511940006773,
"count": 409917,
"self": 70.05158120056194,
"children": {
"TorchPolicy.evaluate": {
"total": 2224.8996128001154,
"count": 754228,
"self": 2224.8996128001154
}
}
},
"workers": {
"total": 7.900382401859872,
"count": 409917,
"self": 0.0,
"children": {
"worker_root": {
"total": 34245.029955599464,
"count": 409917,
"is_parallel": true,
"self": 28381.15848829953,
"children": {
"steps_from_proto": {
"total": 0.04713749999852723,
"count": 40,
"is_parallel": true,
"self": 0.009164100026467281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.03797339997205995,
"count": 160,
"is_parallel": true,
"self": 0.03797339997205995
}
}
},
"UnityEnvironment.step": {
"total": 5863.824329799937,
"count": 409917,
"is_parallel": true,
"self": 313.51908039884256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 237.79024300042062,
"count": 409917,
"is_parallel": true,
"self": 237.79024300042062
},
"communicator.exchange": {
"total": 4308.629009600052,
"count": 409917,
"is_parallel": true,
"self": 4308.629009600052
},
"steps_from_proto": {
"total": 1003.8859968006221,
"count": 819834,
"is_parallel": true,
"self": 195.16162870213873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 808.7243680984834,
"count": 3279336,
"is_parallel": true,
"self": 808.7243680984834
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 24673.604838800406,
"count": 409917,
"self": 87.52570980115706,
"children": {
"process_trajectory": {
"total": 2400.457999399211,
"count": 409917,
"self": 2398.1267318992122,
"children": {
"RLTrainer._checkpoint": {
"total": 2.3312674999988303,
"count": 12,
"self": 2.3312674999988303
}
}
},
"_update_policy": {
"total": 22185.621129600037,
"count": 289,
"self": 1728.1840312997883,
"children": {
"TorchPOCAOptimizer.update": {
"total": 20457.437098300248,
"count": 14450,
"self": 20457.437098300248
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.999995770864189e-07,
"count": 1,
"self": 8.999995770864189e-07
},
"TrainerController._save_models": {
"total": 0.19010290000005625,
"count": 1,
"self": 0.02187430000049062,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16822859999956563,
"count": 1,
"self": 0.16822859999956563
}
}
}
}
}
}
}