poca-SoccerTwos / run_logs /timers.json
HilbertS's picture
Push about 3.9m steps of SoccerTwos
8921bc6
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.9089889526367188,
"min": 1.8442237377166748,
"max": 3.213865041732788,
"count": 472
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 35919.53515625,
"min": 29317.10546875,
"max": 120344.625,
"count": 472
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 62.17948717948718,
"min": 42.51304347826087,
"max": 999.0,
"count": 472
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19400.0,
"min": 11112.0,
"max": 28436.0,
"count": 472
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1556.9494059513054,
"min": 1184.4253004330594,
"max": 1576.660508881427,
"count": 471
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 242884.10732840362,
"min": 2370.6947943219175,
"max": 334525.03998778446,
"count": 471
},
"SoccerTwos.Step.mean": {
"value": 5039949.0,
"min": 329805.0,
"max": 5039949.0,
"count": 472
},
"SoccerTwos.Step.sum": {
"value": 5039949.0,
"min": 329805.0,
"max": 5039949.0,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.010436630807816982,
"min": -0.09697045385837555,
"max": 0.1714733988046646,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.6385509967803955,
"min": -16.600444793701172,
"max": 23.41659164428711,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.01028787437826395,
"min": -0.09972328692674637,
"max": 0.17430460453033447,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.6151962280273438,
"min": -17.1435546875,
"max": 23.17365837097168,
"count": 472
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 472
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.10489171933216654,
"min": -0.5669750012457371,
"max": 0.44391110796987276,
"count": 472
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 16.467999935150146,
"min": -50.66320013999939,
"max": 46.512000262737274,
"count": 472
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.10489171933216654,
"min": -0.5669750012457371,
"max": 0.44391110796987276,
"count": 472
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 16.467999935150146,
"min": -50.66320013999939,
"max": 46.512000262737274,
"count": 472
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 472
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 472
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.016275092681947476,
"min": 0.010151559529488926,
"max": 0.024196836646297015,
"count": 227
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.016275092681947476,
"min": 0.010151559529488926,
"max": 0.024196836646297015,
"count": 227
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09684030537803968,
"min": 0.0013416305688830714,
"max": 0.11689281612634658,
"count": 227
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09684030537803968,
"min": 0.0013416305688830714,
"max": 0.11689281612634658,
"count": 227
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09833643784125647,
"min": 0.0013579658038603763,
"max": 0.11826808328429858,
"count": 227
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09833643784125647,
"min": 0.0013579658038603763,
"max": 0.11826808328429858,
"count": 227
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 227
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 227
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 227
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 227
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 227
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 227
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688468546",
"python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --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+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688485154"
},
"total": 16607.525235416368,
"count": 1,
"self": 0.013366627972573042,
"children": {
"run_training.setup": {
"total": 0.015603977721184492,
"count": 1,
"self": 0.015603977721184492
},
"TrainerController.start_learning": {
"total": 16607.496264810674,
"count": 1,
"self": 8.919515123125166,
"children": {
"TrainerController._reset_env": {
"total": 1.5175714301876724,
"count": 25,
"self": 1.5175714301876724
},
"TrainerController.advance": {
"total": 16596.756896799896,
"count": 322264,
"self": 7.916705624666065,
"children": {
"env_step": {
"total": 5911.727526604664,
"count": 322264,
"self": 4514.543463871349,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1392.023328505922,
"count": 322264,
"self": 49.78212635125965,
"children": {
"TorchPolicy.evaluate": {
"total": 1342.2412021546625,
"count": 595496,
"self": 1342.2412021546625
}
}
},
"workers": {
"total": 5.1607342273928225,
"count": 322264,
"self": 0.0,
"children": {
"worker_root": {
"total": 16555.016848264262,
"count": 322264,
"is_parallel": true,
"self": 12923.445410506334,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00312175415456295,
"count": 2,
"is_parallel": true,
"self": 0.0008582943119108677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022634598426520824,
"count": 8,
"is_parallel": true,
"self": 0.0022634598426520824
}
}
},
"UnityEnvironment.step": {
"total": 0.026854357682168484,
"count": 1,
"is_parallel": true,
"self": 0.0006880271248519421,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005317311733961105,
"count": 1,
"is_parallel": true,
"self": 0.0005317311733961105
},
"communicator.exchange": {
"total": 0.023468355182558298,
"count": 1,
"is_parallel": true,
"self": 0.023468355182558298
},
"steps_from_proto": {
"total": 0.002166244201362133,
"count": 2,
"is_parallel": true,
"self": 0.000483611598610878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001682632602751255,
"count": 8,
"is_parallel": true,
"self": 0.001682632602751255
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.053547489922493696,
"count": 48,
"is_parallel": true,
"self": 0.010899828281253576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.04264766164124012,
"count": 192,
"is_parallel": true,
"self": 0.04264766164124012
}
}
},
"UnityEnvironment.step": {
"total": 3631.5178902680054,
"count": 322263,
"is_parallel": true,
"self": 189.9846967374906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 131.83427887735888,
"count": 322263,
"is_parallel": true,
"self": 131.83427887735888
},
"communicator.exchange": {
"total": 2676.0341983493418,
"count": 322263,
"is_parallel": true,
"self": 2676.0341983493418
},
"steps_from_proto": {
"total": 633.6647163038142,
"count": 644526,
"is_parallel": true,
"self": 126.69072948535904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 506.97398681845516,
"count": 2578104,
"is_parallel": true,
"self": 506.97398681845516
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 10677.112664570566,
"count": 322264,
"self": 69.58496827818453,
"children": {
"process_trajectory": {
"total": 1633.3974608271383,
"count": 322264,
"self": 1630.1399948387407,
"children": {
"RLTrainer._checkpoint": {
"total": 3.2574659883975983,
"count": 10,
"self": 3.2574659883975983
}
}
},
"_update_policy": {
"total": 8974.130235465243,
"count": 228,
"self": 946.202926828526,
"children": {
"TorchPOCAOptimizer.update": {
"total": 8027.9273086367175,
"count": 6840,
"self": 8027.9273086367175
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.514570951461792e-06,
"count": 1,
"self": 2.514570951461792e-06
},
"TrainerController._save_models": {
"total": 0.30227894289419055,
"count": 1,
"self": 0.005925939884036779,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29635300301015377,
"count": 1,
"self": 0.29635300301015377
}
}
}
}
}
}
}