|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 2.0817551612854004, |
|
"min": 2.050828218460083, |
|
"max": 2.275116205215454, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 42900.8125, |
|
"min": 39650.84375, |
|
"max": 50390.9765625, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 39.314516129032256, |
|
"min": 33.28082191780822, |
|
"max": 57.25581395348837, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19500.0, |
|
"min": 16104.0, |
|
"max": 20308.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1514.2101837328041, |
|
"min": 1476.4009957931617, |
|
"max": 1527.4014633986794, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 375524.12556573545, |
|
"min": 256817.66796581444, |
|
"max": 441113.2119379982, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 10339990.0, |
|
"min": 8959951.0, |
|
"max": 10339990.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 10339990.0, |
|
"min": 8959951.0, |
|
"max": 10339990.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.01461908221244812, |
|
"min": -0.04508669674396515, |
|
"max": 0.06564339250326157, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 3.6109132766723633, |
|
"min": -9.310239791870117, |
|
"max": 16.082632064819336, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.015170346014201641, |
|
"min": -0.04868944361805916, |
|
"max": 0.06690935045480728, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 3.7470755577087402, |
|
"min": -9.785125732421875, |
|
"max": 16.198457717895508, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.014383805908172237, |
|
"min": -0.1816229159012437, |
|
"max": 0.21367312527963245, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 3.5528000593185425, |
|
"min": -36.445600390434265, |
|
"max": 48.50379943847656, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.014383805908172237, |
|
"min": -0.1816229159012437, |
|
"max": 0.21367312527963245, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 3.5528000593185425, |
|
"min": -36.445600390434265, |
|
"max": 48.50379943847656, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 139 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.014852080177903796, |
|
"min": 0.009855266399487543, |
|
"max": 0.022194832651378723, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.014852080177903796, |
|
"min": 0.009855266399487543, |
|
"max": 0.022194832651378723, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.08246669918298721, |
|
"min": 0.07240680480996768, |
|
"max": 0.0872135025759538, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.08246669918298721, |
|
"min": 0.07240680480996768, |
|
"max": 0.0872135025759538, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.08406391814351082, |
|
"min": 0.07332472875714302, |
|
"max": 0.08962557539343834, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.08406391814351082, |
|
"min": 0.07332472875714302, |
|
"max": 0.08962557539343834, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 67 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 67 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1691323071", |
|
"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 --resume --torch-device=cpu", |
|
"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": "1691328379" |
|
}, |
|
"total": 5307.499628232, |
|
"count": 1, |
|
"self": 0.5378562470004908, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.06018139100001463, |
|
"count": 1, |
|
"self": 0.06018139100001463 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 5306.901590594, |
|
"count": 1, |
|
"self": 3.954543449065568, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.757532165000839, |
|
"count": 8, |
|
"self": 1.757532165000839 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 5301.185609296934, |
|
"count": 99781, |
|
"self": 4.008114537936308, |
|
"children": { |
|
"env_step": { |
|
"total": 2931.331986786951, |
|
"count": 99781, |
|
"self": 2508.7911618191483, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 420.3306268819065, |
|
"count": 99781, |
|
"self": 18.73769292570705, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 401.59293395619943, |
|
"count": 175010, |
|
"self": 401.59293395619943 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.2101980858960815, |
|
"count": 99780, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 5284.2023605070735, |
|
"count": 99780, |
|
"is_parallel": true, |
|
"self": 3188.8961787200533, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004170569000052637, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0011218869999538583, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003048682000098779, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003048682000098779 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04688210699987394, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0013496169997324614, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0006175339999572316, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006175339999572316 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.040462964000198554, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.040462964000198554 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.004451991999985694, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0008053609999478795, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0036466310000378144, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0036466310000378144 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.019279038001741355, |
|
"count": 14, |
|
"is_parallel": true, |
|
"self": 0.0034742869997899106, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.015804751001951445, |
|
"count": 56, |
|
"is_parallel": true, |
|
"self": 0.015804751001951445 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2095.2869027490187, |
|
"count": 99779, |
|
"is_parallel": true, |
|
"self": 125.02009742788687, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 64.16027218404838, |
|
"count": 99779, |
|
"is_parallel": true, |
|
"self": 64.16027218404838 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1498.7004830649933, |
|
"count": 99779, |
|
"is_parallel": true, |
|
"self": 1498.7004830649933 |
|
}, |
|
"steps_from_proto": { |
|
"total": 407.40605007209024, |
|
"count": 199558, |
|
"is_parallel": true, |
|
"self": 72.04748076905344, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 335.3585693030368, |
|
"count": 798232, |
|
"is_parallel": true, |
|
"self": 335.3585693030368 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2365.8455079720466, |
|
"count": 99780, |
|
"self": 25.670958199969846, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 507.6338691290741, |
|
"count": 99780, |
|
"self": 506.59619934807483, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.0376697809992947, |
|
"count": 3, |
|
"self": 1.0376697809992947 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1832.5406806430028, |
|
"count": 67, |
|
"self": 356.4519601630159, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 1476.088720479987, |
|
"count": 2010, |
|
"self": 1476.088720479987 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.538999640615657e-06, |
|
"count": 1, |
|
"self": 1.538999640615657e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0039041439995344263, |
|
"count": 1, |
|
"self": 6.911199943715474e-05, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0038350320000972715, |
|
"count": 1, |
|
"self": 0.0038350320000972715 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |