|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.24275541305542, |
|
"min": 3.24275541305542, |
|
"max": 3.295746326446533, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 38186.6875, |
|
"min": 38186.6875, |
|
"max": 105463.8828125, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 606.7777777777778, |
|
"min": 520.3, |
|
"max": 999.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 21844.0, |
|
"min": 7992.0, |
|
"max": 28660.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1201.8547722852395, |
|
"min": 1200.5792730868427, |
|
"max": 1201.8547722852395, |
|
"count": 9 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 12018.547722852396, |
|
"min": 2401.464661808079, |
|
"max": 19225.90452399253, |
|
"count": 9 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 99568.0, |
|
"min": 9570.0, |
|
"max": 99568.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 99568.0, |
|
"min": 9570.0, |
|
"max": 99568.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.029951417818665504, |
|
"min": 0.02901970036327839, |
|
"max": 0.048930633813142776, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 0.509174108505249, |
|
"min": 0.38262397050857544, |
|
"max": 0.6850288510322571, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.028144966810941696, |
|
"min": 0.027174649760127068, |
|
"max": 0.04895564541220665, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 0.47846442461013794, |
|
"min": 0.3738063871860504, |
|
"max": 0.6853790283203125, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.2860470607000239, |
|
"min": -0.5863199979066849, |
|
"max": 0.14454545757987283, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -4.862800031900406, |
|
"min": -11.726399958133698, |
|
"max": 1.6668000221252441, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.2860470607000239, |
|
"min": -0.5863199979066849, |
|
"max": 0.14454545757987283, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -4.862800031900406, |
|
"min": -11.726399958133698, |
|
"max": 1.6668000221252441, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 10 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.016999145213048905, |
|
"min": 0.014864533439200993, |
|
"max": 0.021333938790485264, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.016999145213048905, |
|
"min": 0.014864533439200993, |
|
"max": 0.021333938790485264, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.008634821216886242, |
|
"min": 0.0021723957305463653, |
|
"max": 0.008634821216886242, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.008634821216886242, |
|
"min": 0.0021723957305463653, |
|
"max": 0.008634821216886242, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.00866512347323199, |
|
"min": 0.0022123285297614833, |
|
"max": 0.00866512347323199, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.00866512347323199, |
|
"min": 0.0022123285297614833, |
|
"max": 0.00866512347323199, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0005000000000000001, |
|
"min": 0.0005000000000000001, |
|
"max": 0.0005000000000000001, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0005000000000000001, |
|
"min": 0.0005000000000000001, |
|
"max": 0.0005000000000000001, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.25, |
|
"min": 0.25, |
|
"max": 0.25, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.25, |
|
"min": 0.25, |
|
"max": 0.25, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 4 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1688137353", |
|
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --force --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", |
|
"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": "1688137582" |
|
}, |
|
"total": 229.2581640599999, |
|
"count": 1, |
|
"self": 0.4278893439998228, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.056540562999998656, |
|
"count": 1, |
|
"self": 0.056540562999998656 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 228.77373415300008, |
|
"count": 1, |
|
"self": 0.17167384600361402, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.496263988999999, |
|
"count": 1, |
|
"self": 4.496263988999999 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 223.85334627399675, |
|
"count": 6638, |
|
"self": 0.1896259219976173, |
|
"children": { |
|
"env_step": { |
|
"total": 184.28574929799936, |
|
"count": 6638, |
|
"self": 146.13848868899447, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 38.044316245003415, |
|
"count": 6638, |
|
"self": 1.1064244529911775, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 36.93789179201224, |
|
"count": 13190, |
|
"self": 36.93789179201224 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.10294436400147333, |
|
"count": 6638, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 227.91117653100514, |
|
"count": 6638, |
|
"is_parallel": true, |
|
"self": 104.47200492099682, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007272525000075802, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.004464704000270103, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002807820999805699, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002807820999805699 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.09490549600002396, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0013274289998435052, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0008129560000043057, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008129560000043057 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.08935578400007671, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.08935578400007671 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.003409327000099438, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0005592380001644415, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0028500889999349965, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0028500889999349965 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 123.43917161000832, |
|
"count": 6637, |
|
"is_parallel": true, |
|
"self": 7.394726979014649, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 4.696676217000459, |
|
"count": 6637, |
|
"is_parallel": true, |
|
"self": 4.696676217000459 |
|
}, |
|
"communicator.exchange": { |
|
"total": 88.05540955599372, |
|
"count": 6637, |
|
"is_parallel": true, |
|
"self": 88.05540955599372 |
|
}, |
|
"steps_from_proto": { |
|
"total": 23.29235885799949, |
|
"count": 13274, |
|
"is_parallel": true, |
|
"self": 3.879779087021575, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 19.412579770977914, |
|
"count": 53096, |
|
"is_parallel": true, |
|
"self": 19.412579770977914 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 39.37797105399977, |
|
"count": 6638, |
|
"self": 1.3050220389972083, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 10.576377912002613, |
|
"count": 6638, |
|
"self": 10.576377912002613 |
|
}, |
|
"_update_policy": { |
|
"total": 27.49657110299995, |
|
"count": 4, |
|
"self": 17.63281560999974, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 9.863755493000212, |
|
"count": 129, |
|
"self": 9.863755493000212 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.629998203308787e-07, |
|
"count": 1, |
|
"self": 9.629998203308787e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.25244908099989516, |
|
"count": 1, |
|
"self": 0.0018825219997324893, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.25056655900016267, |
|
"count": 1, |
|
"self": 0.25056655900016267 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |