Yudkowsky / run_logs /timers.json
CzarnyRycerz's picture
First Push`
ca9e455
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.6468665599823,
"min": 2.541663646697998,
"max": 2.871713161468506,
"count": 85
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 25748.716796875,
"min": 8567.4287109375,
"max": 36632.6953125,
"count": 85
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 67.88888888888889,
"min": 40.714285714285715,
"max": 135.77777777777777,
"count": 85
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 9776.0,
"min": 1140.0,
"max": 10680.0,
"count": 85
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 2375.3358173178267,
"min": 2235.5589987679004,
"max": 2381.703469709723,
"count": 85
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 171024.17884688353,
"min": 31488.55584315862,
"max": 260906.22136500393,
"count": 85
},
"SoccerTwos.Step.mean": {
"value": 21499985.0,
"min": 21079986.0,
"max": 21499985.0,
"count": 85
},
"SoccerTwos.Step.sum": {
"value": 21499985.0,
"min": 21079986.0,
"max": 21499985.0,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.13880492746829987,
"min": -0.029741428792476654,
"max": 0.25591257214546204,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 9.9939546585083,
"min": -2.3920230865478516,
"max": 20.130294799804688,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.13861840963363647,
"min": -0.03013807162642479,
"max": 0.2552904188632965,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 9.980525016784668,
"min": -2.4623286724090576,
"max": 20.086620330810547,
"count": 85
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 85
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.4470666680071089,
"min": -0.41783611062500214,
"max": 0.7164689590191019,
"count": 85
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 32.18880009651184,
"min": -31.340400218963623,
"max": 52.656800270080566,
"count": 85
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.4470666680071089,
"min": -0.41783611062500214,
"max": 0.7164689590191019,
"count": 85
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 32.18880009651184,
"min": -31.340400218963623,
"max": 52.656800270080566,
"count": 85
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 85
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 85
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015227855048821463,
"min": 0.011556042971399923,
"max": 0.020092821136737864,
"count": 20
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015227855048821463,
"min": 0.011556042971399923,
"max": 0.020092821136737864,
"count": 20
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09070096512635549,
"min": 0.05192163946727912,
"max": 0.09316741997996966,
"count": 20
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09070096512635549,
"min": 0.05192163946727912,
"max": 0.09316741997996966,
"count": 20
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09092343325416247,
"min": 0.05207549768189589,
"max": 0.09350195775429408,
"count": 20
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09092343325416247,
"min": 0.05207549768189589,
"max": 0.09350195775429408,
"count": 20
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 1.113511257069722e-07,
"min": 1.113511257069722e-07,
"max": 5.578772559046528e-06,
"count": 20
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 1.113511257069722e-07,
"min": 1.113511257069722e-07,
"max": 5.578772559046528e-06,
"count": 20
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.25,
"min": 0.25,
"max": 0.25,
"count": 20
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.25,
"min": 0.25,
"max": 0.25,
"count": 20
},
"SoccerTwos.Policy.Beta.mean": {
"value": 1.3704663720930079e-05,
"min": 1.3704663720930079e-05,
"max": 0.00019576985813953539,
"count": 20
},
"SoccerTwos.Policy.Beta.sum": {
"value": 1.3704663720930079e-05,
"min": 1.3704663720930079e-05,
"max": 0.00019576985813953539,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1694398166",
"python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1694401048"
},
"total": 2881.8619468,
"count": 1,
"self": 0.39316980000012336,
"children": {
"run_training.setup": {
"total": 0.14249270000000003,
"count": 1,
"self": 0.14249270000000003
},
"TrainerController.start_learning": {
"total": 2881.3262843,
"count": 1,
"self": 0.9726952999972127,
"children": {
"TrainerController._reset_env": {
"total": 5.015679300000025,
"count": 4,
"self": 5.015679300000025
},
"TrainerController.advance": {
"total": 2875.053183500003,
"count": 28831,
"self": 1.0066420000871403,
"children": {
"env_step": {
"total": 763.5760517999634,
"count": 28831,
"self": 499.511171099941,
"children": {
"SubprocessEnvManager._take_step": {
"total": 263.4686580999995,
"count": 28831,
"self": 7.140219500018418,
"children": {
"TorchPolicy.evaluate": {
"total": 256.3284385999811,
"count": 52834,
"self": 256.3284385999811
}
}
},
"workers": {
"total": 0.596222600022843,
"count": 28831,
"self": 0.0,
"children": {
"worker_root": {
"total": 2874.6264508000168,
"count": 28831,
"is_parallel": true,
"self": 2490.8024807999996,
"children": {
"steps_from_proto": {
"total": 0.010278200000094273,
"count": 8,
"is_parallel": true,
"self": 0.0023597000005421975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007918499999552076,
"count": 32,
"is_parallel": true,
"self": 0.007918499999552076
}
}
},
"UnityEnvironment.step": {
"total": 383.813691800017,
"count": 28831,
"is_parallel": true,
"self": 20.69146799995832,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.049770600046077,
"count": 28831,
"is_parallel": true,
"self": 21.049770600046077
},
"communicator.exchange": {
"total": 274.51462600000644,
"count": 28831,
"is_parallel": true,
"self": 274.51462600000644
},
"steps_from_proto": {
"total": 67.55782720000619,
"count": 57662,
"is_parallel": true,
"self": 15.188267900029203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.369559299976984,
"count": 230648,
"is_parallel": true,
"self": 52.369559299976984
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2110.4704896999524,
"count": 28831,
"self": 7.441301699985161,
"children": {
"process_trajectory": {
"total": 285.196211699967,
"count": 28831,
"self": 284.83748069996676,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3587310000002617,
"count": 1,
"self": 0.3587310000002617
}
}
},
"_update_policy": {
"total": 1817.8329763000004,
"count": 20,
"self": 120.90873570000258,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1696.9242405999978,
"count": 600,
"self": 1696.9242405999978
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.100000190490391e-06,
"count": 1,
"self": 1.100000190490391e-06
},
"TrainerController._save_models": {
"total": 0.2847250999998323,
"count": 1,
"self": 0.014907899999798246,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26981720000003406,
"count": 1,
"self": 0.26981720000003406
}
}
}
}
}
}
}