|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 2.3667643070220947, |
|
"min": 2.33071231842041, |
|
"max": 2.5206995010375977, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 47562.49609375, |
|
"min": 44078.4296875, |
|
"max": 55899.03125, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 48.88, |
|
"min": 43.7304347826087, |
|
"max": 61.69620253164557, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19552.0, |
|
"min": 18684.0, |
|
"max": 20208.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1470.7483954716015, |
|
"min": 1435.3163092525817, |
|
"max": 1490.4149327494056, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 294149.6790943203, |
|
"min": 230435.66739658496, |
|
"max": 335717.66091586347, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 6999984.0, |
|
"min": 6509978.0, |
|
"max": 6999984.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 6999984.0, |
|
"min": 6509978.0, |
|
"max": 6999984.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.07726456969976425, |
|
"min": -0.030845150351524353, |
|
"max": 0.07726456969976425, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 15.452914237976074, |
|
"min": -6.045649528503418, |
|
"max": 15.91751480102539, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.07707680016756058, |
|
"min": -0.0268353670835495, |
|
"max": 0.07984796911478043, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 15.415359497070312, |
|
"min": -5.259731769561768, |
|
"max": 16.76807403564453, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.18601200073957444, |
|
"min": -0.22530110065753645, |
|
"max": 0.3014857155936105, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 37.20240014791489, |
|
"min": -41.00480031967163, |
|
"max": 63.3120002746582, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.18601200073957444, |
|
"min": -0.22530110065753645, |
|
"max": 0.3014857155936105, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 37.20240014791489, |
|
"min": -41.00480031967163, |
|
"max": 63.3120002746582, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 50 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.01691505271786203, |
|
"min": 0.012469863990554586, |
|
"max": 0.02095626645217029, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01691505271786203, |
|
"min": 0.012469863990554586, |
|
"max": 0.02095626645217029, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.07490279500683149, |
|
"min": 0.06604709873596827, |
|
"max": 0.08390739584962527, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.07490279500683149, |
|
"min": 0.06604709873596827, |
|
"max": 0.08390739584962527, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.07590456182758014, |
|
"min": 0.06684525907039643, |
|
"max": 0.08611040810743968, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.07590456182758014, |
|
"min": 0.06684525907039643, |
|
"max": 0.08611040810743968, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 24 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 24 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1690891421", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"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": "1690893542" |
|
}, |
|
"total": 2121.240111834999, |
|
"count": 1, |
|
"self": 0.5420148220000556, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04162588399776723, |
|
"count": 1, |
|
"self": 0.04162588399776723 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2120.656471129001, |
|
"count": 1, |
|
"self": 1.5054543152655242, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.4437276519965963, |
|
"count": 4, |
|
"self": 1.4437276519965963 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2117.4951610467397, |
|
"count": 35069, |
|
"self": 1.5695238139524008, |
|
"children": { |
|
"env_step": { |
|
"total": 1155.004338777053, |
|
"count": 35069, |
|
"self": 975.2380251731483, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 178.8851889927828, |
|
"count": 35069, |
|
"self": 8.254970399870217, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 170.63021859291257, |
|
"count": 62828, |
|
"self": 170.63021859291257 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.881124611121777, |
|
"count": 35069, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2109.615471201516, |
|
"count": 35069, |
|
"is_parallel": true, |
|
"self": 1298.5123828862634, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005451203000120586, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0011757169922930188, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.004275486007827567, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.004275486007827567 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.07496027600063826, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0014275090034061577, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0007755869992251974, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007755869992251974 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06163016799837351, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06163016799837351 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.011127011999633396, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0008880850000423379, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.010238926999591058, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.010238926999591058 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.007095673998264829, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0014340400011860766, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.005661633997078752, |
|
"count": 24, |
|
"is_parallel": true, |
|
"self": 0.005661633997078752 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 811.0959926412543, |
|
"count": 35068, |
|
"is_parallel": true, |
|
"self": 48.543254373689706, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 25.37648238968177, |
|
"count": 35068, |
|
"is_parallel": true, |
|
"self": 25.37648238968177 |
|
}, |
|
"communicator.exchange": { |
|
"total": 584.6229807467062, |
|
"count": 35068, |
|
"is_parallel": true, |
|
"self": 584.6229807467062 |
|
}, |
|
"steps_from_proto": { |
|
"total": 152.55327513117663, |
|
"count": 70136, |
|
"is_parallel": true, |
|
"self": 28.184793114080094, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 124.36848201709654, |
|
"count": 280544, |
|
"is_parallel": true, |
|
"self": 124.36848201709654 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 960.9212984557344, |
|
"count": 35069, |
|
"self": 9.931847368385206, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 195.88171612734732, |
|
"count": 35069, |
|
"self": 195.66547433134838, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21624179599893978, |
|
"count": 1, |
|
"self": 0.21624179599893978 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 755.1077349600018, |
|
"count": 24, |
|
"self": 137.47176963701713, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 617.6359653229847, |
|
"count": 720, |
|
"self": 617.6359653229847 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.499999578110874e-07, |
|
"count": 1, |
|
"self": 9.499999578110874e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.21212716499940143, |
|
"count": 1, |
|
"self": 0.0018193489995610435, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2103078159998404, |
|
"count": 1, |
|
"self": 0.2103078159998404 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |