|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.2786707878112793, |
|
"min": 3.2786707878112793, |
|
"max": 3.2957398891448975, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 65783.25, |
|
"min": 36799.3671875, |
|
"max": 105463.625, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 711.8571428571429, |
|
"min": 517.4, |
|
"max": 851.1111111111111, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19932.0, |
|
"min": 10348.0, |
|
"max": 30640.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1197.7616558135978, |
|
"min": 1197.7616558135978, |
|
"max": 1201.004267761486, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 7186.569934881587, |
|
"min": 4795.014108976704, |
|
"max": 9608.034142091888, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 49962.0, |
|
"min": 9338.0, |
|
"max": 49962.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 49962.0, |
|
"min": 9338.0, |
|
"max": 49962.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.012619361281394958, |
|
"min": -0.012619361281394958, |
|
"max": -0.00687957089394331, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.17667105793952942, |
|
"min": -0.17667105793952942, |
|
"max": -0.0894344225525856, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.011918552219867706, |
|
"min": -0.013319244608283043, |
|
"max": -0.009380451403558254, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.1668597310781479, |
|
"min": -0.1731501817703247, |
|
"max": -0.11268052458763123, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.08551428147724696, |
|
"min": -0.39057333370049796, |
|
"max": -0.05263077181119185, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -1.1971999406814575, |
|
"min": -5.858600005507469, |
|
"max": -0.6842000335454941, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.08551428147724696, |
|
"min": -0.39057333370049796, |
|
"max": -0.05263077181119185, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -1.1971999406814575, |
|
"min": -5.858600005507469, |
|
"max": -0.6842000335454941, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.017215008425409906, |
|
"min": 0.016517406818456946, |
|
"max": 0.017215008425409906, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.017215008425409906, |
|
"min": 0.016517406818456946, |
|
"max": 0.017215008425409906, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.00251207381952554, |
|
"min": 0.00251207381952554, |
|
"max": 0.003956934755357603, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.00251207381952554, |
|
"min": 0.00251207381952554, |
|
"max": 0.003956934755357603, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.002503076878686746, |
|
"min": 0.002503076878686746, |
|
"max": 0.003620573513520261, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.002503076878686746, |
|
"min": 0.002503076878686746, |
|
"max": 0.003620573513520261, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 2 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1699932378", |
|
"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=./trained-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.0+cu118", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1699932508" |
|
}, |
|
"total": 129.715209491, |
|
"count": 1, |
|
"self": 0.43902412099998855, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07394515300001103, |
|
"count": 1, |
|
"self": 0.07394515300001103 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 129.202240217, |
|
"count": 1, |
|
"self": 0.07847613100048534, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.054503581000006, |
|
"count": 1, |
|
"self": 9.054503581000006 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 119.81510210999946, |
|
"count": 3599, |
|
"self": 0.09146138200014775, |
|
"children": { |
|
"env_step": { |
|
"total": 102.14246289999963, |
|
"count": 3599, |
|
"self": 76.47072561099756, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 25.623439852002093, |
|
"count": 3599, |
|
"self": 0.5733473930022512, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 25.050092458999842, |
|
"count": 7152, |
|
"self": 25.050092458999842 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.0482974369999738, |
|
"count": 3599, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 128.69726455400084, |
|
"count": 3599, |
|
"is_parallel": true, |
|
"self": 64.04457687800027, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007985775000008744, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.004523333999998158, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0034624410000105854, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0034624410000105854 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06187092399997596, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.001328885999924978, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0008331900000086989, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008331900000086989 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05626728000001435, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05626728000001435 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.003441568000027928, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0005542399999853842, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002887328000042544, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002887328000042544 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 64.65268767600057, |
|
"count": 3598, |
|
"is_parallel": true, |
|
"self": 4.069420069997847, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 2.6072526490007704, |
|
"count": 3598, |
|
"is_parallel": true, |
|
"self": 2.6072526490007704 |
|
}, |
|
"communicator.exchange": { |
|
"total": 45.305001452000454, |
|
"count": 3598, |
|
"is_parallel": true, |
|
"self": 45.305001452000454 |
|
}, |
|
"steps_from_proto": { |
|
"total": 12.671013505001497, |
|
"count": 7196, |
|
"is_parallel": true, |
|
"self": 1.9897029600002725, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 10.681310545001224, |
|
"count": 28784, |
|
"is_parallel": true, |
|
"self": 10.681310545001224 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 17.58117782799968, |
|
"count": 3599, |
|
"self": 0.7245799839987512, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 5.1504714890009495, |
|
"count": 3599, |
|
"self": 5.1504714890009495 |
|
}, |
|
"_update_policy": { |
|
"total": 11.70612635499998, |
|
"count": 2, |
|
"self": 7.134961341999741, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 4.57116501300024, |
|
"count": 60, |
|
"self": 4.57116501300024 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0310000106983352e-06, |
|
"count": 1, |
|
"self": 1.0310000106983352e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2541573640000365, |
|
"count": 1, |
|
"self": 0.0016639620000091782, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.25249340200002734, |
|
"count": 1, |
|
"self": 0.25249340200002734 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |