hmatzner's picture
Push model
3b4de58
raw
history blame
15.6 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5661364793777466,
"min": 1.477481722831726,
"max": 1.7391482591629028,
"count": 337
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 30019.705078125,
"min": 24388.8984375,
"max": 39508.31640625,
"count": 337
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 68.02777777777777,
"min": 50.48453608247423,
"max": 104.22916666666667,
"count": 337
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19592.0,
"min": 18020.0,
"max": 21012.0,
"count": 337
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1576.3947632636791,
"min": 1515.7729898708762,
"max": 1601.8279378996233,
"count": 337
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 227000.8459099698,
"min": 152219.87399136502,
"max": 310479.5281895646,
"count": 337
},
"SoccerTwos.Step.mean": {
"value": 19999996.0,
"min": 16639936.0,
"max": 19999996.0,
"count": 337
},
"SoccerTwos.Step.sum": {
"value": 19999996.0,
"min": 16639936.0,
"max": 19999996.0,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.008787903934717178,
"min": -0.10927960276603699,
"max": 0.06806774437427521,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 1.2654582262039185,
"min": -18.78778648376465,
"max": 9.794180870056152,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.008865590207278728,
"min": -0.11062423139810562,
"max": 0.06936821341514587,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 1.2766449451446533,
"min": -18.432466506958008,
"max": 9.964106559753418,
"count": 337
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 337
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.2185402773320675,
"min": -0.335156163124189,
"max": 0.31588292703395937,
"count": 337
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 31.46979993581772,
"min": -48.93279981613159,
"max": 39.04759967327118,
"count": 337
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.2185402773320675,
"min": -0.335156163124189,
"max": 0.31588292703395937,
"count": 337
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 31.46979993581772,
"min": -48.93279981613159,
"max": 39.04759967327118,
"count": 337
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 337
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 337
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015992676412376266,
"min": 0.011186470620214096,
"max": 0.02480827400383229,
"count": 163
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015992676412376266,
"min": 0.011186470620214096,
"max": 0.02480827400383229,
"count": 163
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09166678786277771,
"min": 0.07575185174743335,
"max": 0.11331327781081199,
"count": 163
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09166678786277771,
"min": 0.07575185174743335,
"max": 0.11331327781081199,
"count": 163
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0933613141377767,
"min": 0.07719420144955318,
"max": 0.11555629149079323,
"count": 163
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0933613141377767,
"min": 0.07719420144955318,
"max": 0.11555629149079323,
"count": 163
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 163
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 163
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 163
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 163
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 163
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 163
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679164755",
"python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/hernanmatzner/miniconda3/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1679177322"
},
"total": 12566.549383333,
"count": 1,
"self": 0.44622429099945293,
"children": {
"run_training.setup": {
"total": 0.017642084000000002,
"count": 1,
"self": 0.017642084000000002
},
"TrainerController.start_learning": {
"total": 12566.085516958,
"count": 1,
"self": 2.0162470147206477,
"children": {
"TrainerController._reset_env": {
"total": 3.9375576250000277,
"count": 18,
"self": 3.9375576250000277
},
"TrainerController.advance": {
"total": 12559.93052073528,
"count": 230504,
"self": 1.7797758961569343,
"children": {
"env_step": {
"total": 10290.271683761172,
"count": 230504,
"self": 10016.810077350046,
"children": {
"SubprocessEnvManager._take_step": {
"total": 271.886888797588,
"count": 230504,
"self": 8.768924450663462,
"children": {
"TorchPolicy.evaluate": {
"total": 263.11796434692457,
"count": 422926,
"self": 263.11796434692457
}
}
},
"workers": {
"total": 1.574717613536964,
"count": 230504,
"self": 0.0,
"children": {
"worker_root": {
"total": 12558.568243594598,
"count": 230504,
"is_parallel": true,
"self": 2787.162318530418,
"children": {
"steps_from_proto": {
"total": 0.024449960000769266,
"count": 36,
"is_parallel": true,
"self": 0.0028774990085209673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0215724609922483,
"count": 144,
"is_parallel": true,
"self": 0.0215724609922483
}
}
},
"UnityEnvironment.step": {
"total": 9771.38147510418,
"count": 230504,
"is_parallel": true,
"self": 25.74129883587375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 171.27501271591703,
"count": 230504,
"is_parallel": true,
"self": 171.27501271591703
},
"communicator.exchange": {
"total": 9203.123808036773,
"count": 230504,
"is_parallel": true,
"self": 9203.123808036773
},
"steps_from_proto": {
"total": 371.2413555156154,
"count": 461008,
"is_parallel": true,
"self": 39.16404116959342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 332.077314346022,
"count": 1844032,
"is_parallel": true,
"self": 332.077314346022
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2267.879061077953,
"count": 230504,
"self": 18.141156143781245,
"children": {
"process_trajectory": {
"total": 416.9514230941611,
"count": 230504,
"self": 414.3548810111604,
"children": {
"RLTrainer._checkpoint": {
"total": 2.5965420830007133,
"count": 7,
"self": 2.5965420830007133
}
}
},
"_update_policy": {
"total": 1832.7864818400103,
"count": 163,
"self": 214.868548903989,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1617.9179329360213,
"count": 4890,
"self": 1617.9179329360213
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.3299875212833285e-07,
"count": 1,
"self": 3.3299875212833285e-07
},
"TrainerController._save_models": {
"total": 0.20119125000019267,
"count": 1,
"self": 0.0019096670002909377,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19928158299990173,
"count": 1,
"self": 0.19928158299990173
}
}
}
}
}
}
}