|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.8366409540176392, |
|
"min": 1.8191382884979248, |
|
"max": 2.2652885913848877, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 35674.9140625, |
|
"min": 33638.78125, |
|
"max": 51544.1953125, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 53.62222222222222, |
|
"min": 42.9375, |
|
"max": 74.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19304.0, |
|
"min": 16328.0, |
|
"max": 20732.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1366.1017227198731, |
|
"min": 1198.6892309915056, |
|
"max": 1366.1017227198731, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 245898.31008957716, |
|
"min": 162906.44196233, |
|
"max": 292160.6642892341, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 4999958.0, |
|
"min": 2019995.0, |
|
"max": 4999958.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 4999958.0, |
|
"min": 2019995.0, |
|
"max": 4999958.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.05829504877328873, |
|
"min": -0.11307865381240845, |
|
"max": 0.12428557127714157, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 10.493108749389648, |
|
"min": -18.205663681030273, |
|
"max": 20.06940460205078, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.05640903115272522, |
|
"min": -0.12473158538341522, |
|
"max": 0.12447022646665573, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 10.15362548828125, |
|
"min": -20.081785202026367, |
|
"max": 20.232776641845703, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.12275777724054125, |
|
"min": -0.3071284926803418, |
|
"max": 0.34021734054378, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 22.096399903297424, |
|
"min": -55.9987998008728, |
|
"max": 58.857599914073944, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.12275777724054125, |
|
"min": -0.3071284926803418, |
|
"max": 0.34021734054378, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 22.096399903297424, |
|
"min": -55.9987998008728, |
|
"max": 58.857599914073944, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 299 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.017318982321497364, |
|
"min": 0.010958337449119426, |
|
"max": 0.0258120413365153, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.017318982321497364, |
|
"min": 0.010958337449119426, |
|
"max": 0.0258120413365153, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10514670958121618, |
|
"min": 0.08302166983485222, |
|
"max": 0.11510108535488446, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10514670958121618, |
|
"min": 0.08302166983485222, |
|
"max": 0.11510108535488446, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.1068361500898997, |
|
"min": 0.0843203733364741, |
|
"max": 0.1171369065841039, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.1068361500898997, |
|
"min": 0.0843203733364741, |
|
"max": 0.1171369065841039, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 145 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 145 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1703594557", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.2+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1703601981" |
|
}, |
|
"total": 7423.32795043, |
|
"count": 1, |
|
"self": 0.8187268939991554, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.052145051000479725, |
|
"count": 1, |
|
"self": 0.052145051000479725 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7422.457078485, |
|
"count": 1, |
|
"self": 5.591342118945249, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.3483719270025176, |
|
"count": 16, |
|
"self": 2.3483719270025176 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7414.170145946055, |
|
"count": 207919, |
|
"self": 5.943435315667557, |
|
"children": { |
|
"env_step": { |
|
"total": 5753.48616998604, |
|
"count": 207919, |
|
"self": 4455.678779883493, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 1294.3799755227737, |
|
"count": 207919, |
|
"self": 35.312345244953576, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 1259.0676302778202, |
|
"count": 374958, |
|
"self": 1259.0676302778202 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 3.42741457977354, |
|
"count": 207919, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7405.979755484864, |
|
"count": 207919, |
|
"is_parallel": true, |
|
"self": 3648.0395091438877, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002977608000037435, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0008099170008790679, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002167690999158367, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002167690999158367 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04280118200040306, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0012480430013965815, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0009572049993948895, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009572049993948895 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.036872446999950625, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.036872446999950625 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.003723486999660963, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0006542189985339064, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0030692680011270568, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0030692680011270568 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.03471507300037047, |
|
"count": 30, |
|
"is_parallel": true, |
|
"self": 0.007339705994127144, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.027375367006243323, |
|
"count": 120, |
|
"is_parallel": true, |
|
"self": 0.027375367006243323 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3757.9055312679757, |
|
"count": 207918, |
|
"is_parallel": true, |
|
"self": 238.62076344725392, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 161.03608339312086, |
|
"count": 207918, |
|
"is_parallel": true, |
|
"self": 161.03608339312086 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2605.5229129148893, |
|
"count": 207918, |
|
"is_parallel": true, |
|
"self": 2605.5229129148893 |
|
}, |
|
"steps_from_proto": { |
|
"total": 752.7257715127116, |
|
"count": 415836, |
|
"is_parallel": true, |
|
"self": 125.75205440297304, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 626.9737171097386, |
|
"count": 1663344, |
|
"is_parallel": true, |
|
"self": 626.9737171097386 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1654.7405406443468, |
|
"count": 207919, |
|
"self": 41.082131978872894, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 780.9657481374725, |
|
"count": 207919, |
|
"self": 779.4602844554738, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.5054636819986627, |
|
"count": 6, |
|
"self": 1.5054636819986627 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 832.6926605280014, |
|
"count": 145, |
|
"self": 493.94772783309145, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 338.74493269490995, |
|
"count": 4350, |
|
"self": 338.74493269490995 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.3449989637592807e-06, |
|
"count": 1, |
|
"self": 1.3449989637592807e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.34721714799889014, |
|
"count": 1, |
|
"self": 0.003982193999036099, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.34323495399985404, |
|
"count": 1, |
|
"self": 0.34323495399985404 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |