poca-SoccerTwos / run_logs /timers.json
guocheng66's picture
First Push
19e81c6
raw
history blame
18.7 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2498252391815186,
"min": 3.2498252391815186,
"max": 3.2957494258880615,
"count": 16
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 68012.34375,
"min": 40204.31640625,
"max": 105463.984375,
"count": 16
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 831.4,
"min": 644.5,
"max": 999.0,
"count": 16
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 16628.0,
"min": 14772.0,
"max": 26372.0,
"count": 16
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1200.011282228457,
"min": 1196.9986603914529,
"max": 1201.6990760912279,
"count": 11
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 4800.045128913828,
"min": 2399.965563437694,
"max": 12016.990760912278,
"count": 11
},
"SoccerTwos.Step.mean": {
"value": 159250.0,
"min": 9202.0,
"max": 159250.0,
"count": 16
},
"SoccerTwos.Step.sum": {
"value": 159250.0,
"min": 9202.0,
"max": 159250.0,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.008204853162169456,
"min": 0.0027194288559257984,
"max": 0.06095992028713226,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.09025338292121887,
"min": 0.03535257652401924,
"max": 0.7924005389213562,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.008218503557145596,
"min": 0.0029141937848180532,
"max": 0.06097675859928131,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.09040354192256927,
"min": 0.03788451850414276,
"max": 0.7926248908042908,
"count": 16
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 16
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.13785454630851746,
"min": -0.36363636363636365,
"max": 0.21687692403793335,
"count": 16
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -1.516400009393692,
"min": -4.251600027084351,
"max": 2.8194000124931335,
"count": 16
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.13785454630851746,
"min": -0.36363636363636365,
"max": 0.21687692403793335,
"count": 16
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -1.516400009393692,
"min": -4.251600027084351,
"max": 2.8194000124931335,
"count": 16
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.014225690786649163,
"min": 0.014225690786649163,
"max": 0.0217047512337255,
"count": 7
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.014225690786649163,
"min": 0.014225690786649163,
"max": 0.0217047512337255,
"count": 7
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0009059652307769284,
"min": 0.0008610313307144679,
"max": 0.005003788516235849,
"count": 7
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0009059652307769284,
"min": 0.0008610313307144679,
"max": 0.005003788516235849,
"count": 7
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0009158240757339323,
"min": 0.0008748267233992616,
"max": 0.005044405449492236,
"count": 7
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0009158240757339323,
"min": 0.0008748267233992616,
"max": 0.005044405449492236,
"count": 7
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 7
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 7
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 7
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 7
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 7
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 7
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697684702",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697685594"
},
"total": 892.3789655999999,
"count": 1,
"self": 0.37092944300002273,
"children": {
"run_training.setup": {
"total": 0.07751938699993843,
"count": 1,
"self": 0.07751938699993843
},
"TrainerController.start_learning": {
"total": 891.9305167699999,
"count": 1,
"self": 0.3805751149968728,
"children": {
"TrainerController._reset_env": {
"total": 1.588794888999928,
"count": 1,
"self": 1.588794888999928
},
"TrainerController.advance": {
"total": 889.4396380340033,
"count": 10891,
"self": 0.44354376202591084,
"children": {
"env_step": {
"total": 369.67385742198667,
"count": 10891,
"self": 298.68240304696565,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.74381621701491,
"count": 10891,
"self": 3.0389947630369534,
"children": {
"TorchPolicy.evaluate": {
"total": 67.70482145397796,
"count": 21642,
"self": 67.70482145397796
}
}
},
"workers": {
"total": 0.24763815800611155,
"count": 10890,
"self": 0.0,
"children": {
"worker_root": {
"total": 890.1284948959899,
"count": 10890,
"is_parallel": true,
"self": 642.1720417669906,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009498120000216659,
"count": 2,
"is_parallel": true,
"self": 0.005277394000358981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004220725999857677,
"count": 8,
"is_parallel": true,
"self": 0.004220725999857677
}
}
},
"UnityEnvironment.step": {
"total": 0.07662100500010638,
"count": 1,
"is_parallel": true,
"self": 0.0015879869999935181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0014820999999756168,
"count": 1,
"is_parallel": true,
"self": 0.0014820999999756168
},
"communicator.exchange": {
"total": 0.06878995500005658,
"count": 1,
"is_parallel": true,
"self": 0.06878995500005658
},
"steps_from_proto": {
"total": 0.004760963000080665,
"count": 2,
"is_parallel": true,
"self": 0.0007841609999559296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003976802000124735,
"count": 8,
"is_parallel": true,
"self": 0.003976802000124735
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.95645312899933,
"count": 10889,
"is_parallel": true,
"self": 15.642344614018157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.171408972998279,
"count": 10889,
"is_parallel": true,
"self": 9.171408972998279
},
"communicator.exchange": {
"total": 175.8291073189905,
"count": 10889,
"is_parallel": true,
"self": 175.8291073189905
},
"steps_from_proto": {
"total": 47.31359222299238,
"count": 21778,
"is_parallel": true,
"self": 8.092771005980012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.22082121701237,
"count": 87112,
"is_parallel": true,
"self": 39.22082121701237
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 519.3222368499908,
"count": 10890,
"self": 3.5953262919724693,
"children": {
"process_trajectory": {
"total": 69.1600442570184,
"count": 10890,
"self": 69.1600442570184
},
"_update_policy": {
"total": 446.5668663009999,
"count": 7,
"self": 30.450832707001382,
"children": {
"TorchPOCAOptimizer.update": {
"total": 416.1160335939985,
"count": 210,
"self": 416.1160335939985
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9579999843699625e-06,
"count": 1,
"self": 1.9579999843699625e-06
},
"TrainerController._save_models": {
"total": 0.5215067739998176,
"count": 1,
"self": 0.008645491999686783,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5128612820001308,
"count": 1,
"self": 0.5128612820001308
}
}
}
}
}
}
}