|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.2418689727783203, |
|
"min": 3.1966044902801514, |
|
"max": 3.295738935470581, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 44089.41796875, |
|
"min": 29153.033203125, |
|
"max": 105463.59375, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 938.0, |
|
"min": 485.4, |
|
"max": 999.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 18760.0, |
|
"min": 16212.0, |
|
"max": 23276.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1195.405863227191, |
|
"min": 1193.407974261606, |
|
"max": 1202.563785842107, |
|
"count": 32 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 2390.811726454382, |
|
"min": 2388.1345341231226, |
|
"max": 16800.000921159233, |
|
"count": 32 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 339818.0, |
|
"min": 9510.0, |
|
"max": 339818.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 339818.0, |
|
"min": 9510.0, |
|
"max": 339818.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.0064717428758740425, |
|
"min": -0.013049962930381298, |
|
"max": 0.06881744414567947, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.06471742689609528, |
|
"min": -0.20288750529289246, |
|
"max": 1.032261610031128, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.0065886168740689754, |
|
"min": -0.012767443433403969, |
|
"max": 0.06885610520839691, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.06588616967201233, |
|
"min": -0.2042790949344635, |
|
"max": 1.0328415632247925, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.0, |
|
"min": -0.6923076923076923, |
|
"max": 0.30119999647140505, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 0.0, |
|
"min": -9.0, |
|
"max": 4.517999947071075, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": -0.6923076923076923, |
|
"max": 0.30119999647140505, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": -9.0, |
|
"max": 4.517999947071075, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 34 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.01841297391122983, |
|
"min": 0.01300939742141054, |
|
"max": 0.0201228869787883, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01841297391122983, |
|
"min": 0.01300939742141054, |
|
"max": 0.0201228869787883, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.0001582189739565365, |
|
"min": 0.0001582189739565365, |
|
"max": 0.006725435331463814, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.0001582189739565365, |
|
"min": 0.0001582189739565365, |
|
"max": 0.006725435331463814, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.0001607902983475166, |
|
"min": 0.0001607902983475166, |
|
"max": 0.006197890259015063, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.0001607902983475166, |
|
"min": 0.0001607902983475166, |
|
"max": 0.006197890259015063, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 16 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1685045154", |
|
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", |
|
"command_line_arguments": "/home/sadra-barikbin/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cpu", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1685049006" |
|
}, |
|
"total": 3851.3453548840007, |
|
"count": 1, |
|
"self": 0.1356319100004839, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.011757823000152712, |
|
"count": 1, |
|
"self": 0.011757823000152712 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3851.197965151, |
|
"count": 1, |
|
"self": 0.686521564945906, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.6295709819996773, |
|
"count": 2, |
|
"self": 1.6295709819996773 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3848.543460912054, |
|
"count": 22583, |
|
"self": 0.718869355069728, |
|
"children": { |
|
"env_step": { |
|
"total": 3108.535672307954, |
|
"count": 22583, |
|
"self": 3004.4388827744433, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 103.69949132260354, |
|
"count": 22583, |
|
"self": 4.58749585557689, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 99.11199546702665, |
|
"count": 44838, |
|
"self": 99.11199546702665 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3972982109071381, |
|
"count": 22582, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3849.5970459510654, |
|
"count": 22582, |
|
"is_parallel": true, |
|
"self": 924.197943497963, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005524146999960067, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0018040919985651271, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0037200550013949396, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0037200550013949396 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.216608486000041, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00032194300001719967, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0025612740000724443, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0025612740000724443 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.20969537000019045, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.20969537000019045 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.004029898999760917, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0006060089990569395, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0034238900007039774, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0034238900007039774 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2925.3954338321037, |
|
"count": 22581, |
|
"is_parallel": true, |
|
"self": 7.69875933412095, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 61.0330529719231, |
|
"count": 22581, |
|
"is_parallel": true, |
|
"self": 61.0330529719231 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2761.053441806006, |
|
"count": 22581, |
|
"is_parallel": true, |
|
"self": 2761.053441806006 |
|
}, |
|
"steps_from_proto": { |
|
"total": 95.61017972005357, |
|
"count": 45162, |
|
"is_parallel": true, |
|
"self": 13.568160792005983, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 82.04201892804758, |
|
"count": 180648, |
|
"is_parallel": true, |
|
"self": 82.04201892804758 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0036686209987237817, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0005391069989855168, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003129513999738265, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003129513999738265 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 739.2889192490302, |
|
"count": 22582, |
|
"self": 4.486709887963116, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 90.76107710406541, |
|
"count": 22582, |
|
"self": 90.76107710406541 |
|
}, |
|
"_update_policy": { |
|
"total": 644.0411322570017, |
|
"count": 16, |
|
"self": 68.02150736899421, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 576.0196248880075, |
|
"count": 480, |
|
"self": 576.0196248880075 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 2.1340001694625244e-06, |
|
"count": 1, |
|
"self": 2.1340001694625244e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.3384095580004214, |
|
"count": 1, |
|
"self": 0.001959322000402608, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3364502360000188, |
|
"count": 1, |
|
"self": 0.3364502360000188 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |