|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 2.2750937938690186, |
|
"min": 2.237426519393921, |
|
"max": 2.4118874073028564, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 45793.08984375, |
|
"min": 42230.7265625, |
|
"max": 57216.2578125, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 56.63953488372093, |
|
"min": 42.29661016949152, |
|
"max": 61.325, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19484.0, |
|
"min": 19048.0, |
|
"max": 20140.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1482.6735168891223, |
|
"min": 1447.8964098134252, |
|
"max": 1498.4113615420426, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 255019.84490492905, |
|
"min": 235665.1365983267, |
|
"max": 350803.6744841606, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 8949979.0, |
|
"min": 8509934.0, |
|
"max": 8949979.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 8949979.0, |
|
"min": 8509934.0, |
|
"max": 8949979.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.004916130565106869, |
|
"min": -0.03196634352207184, |
|
"max": 0.07559280097484589, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.8504905700683594, |
|
"min": -5.49821138381958, |
|
"max": 16.894067764282227, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.0044533200562000275, |
|
"min": -0.03109934739768505, |
|
"max": 0.07799124717712402, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.7704243659973145, |
|
"min": -5.349087715148926, |
|
"max": 16.790143966674805, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.03477225551715476, |
|
"min": -0.21960648588232093, |
|
"max": 0.2603318790160933, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -6.015600204467773, |
|
"min": -40.62719988822937, |
|
"max": 59.616000294685364, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.03477225551715476, |
|
"min": -0.21960648588232093, |
|
"max": 0.2603318790160933, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -6.015600204467773, |
|
"min": -40.62719988822937, |
|
"max": 59.616000294685364, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 45 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.019061286328117908, |
|
"min": 0.013057671172039894, |
|
"max": 0.021450920356437565, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.019061286328117908, |
|
"min": 0.013057671172039894, |
|
"max": 0.021450920356437565, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.08023651391267776, |
|
"min": 0.06944796616832415, |
|
"max": 0.08236863935987154, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.08023651391267776, |
|
"min": 0.06944796616832415, |
|
"max": 0.08236863935987154, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.0812089612086614, |
|
"min": 0.07063307439287504, |
|
"max": 0.08386725783348084, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.0812089612086614, |
|
"min": 0.07063307439287504, |
|
"max": 0.08386725783348084, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 21 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 21 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1691321389", |
|
"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=./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": "1691323056" |
|
}, |
|
"total": 1666.35867087, |
|
"count": 1, |
|
"self": 0.1516258750000361, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0630226039999684, |
|
"count": 1, |
|
"self": 0.0630226039999684 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1666.144022391, |
|
"count": 1, |
|
"self": 1.125772229994709, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.8054959460000646, |
|
"count": 4, |
|
"self": 3.8054959460000646 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1660.728283220005, |
|
"count": 31775, |
|
"self": 1.17107058898182, |
|
"children": { |
|
"env_step": { |
|
"total": 923.7054244490093, |
|
"count": 31775, |
|
"self": 787.9239653509692, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 135.0932160220205, |
|
"count": 31775, |
|
"self": 6.267143035018819, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 128.82607298700168, |
|
"count": 56764, |
|
"self": 128.82607298700168 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.688243076019603, |
|
"count": 31774, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1660.719618600975, |
|
"count": 31774, |
|
"is_parallel": true, |
|
"self": 998.2839195230074, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.009984467000037966, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.005311473000119804, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0046729939999181624, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0046729939999181624 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05700391100003799, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0014013470000122652, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0006023120000122617, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006023120000122617 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04908923200002846, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04908923200002846 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.005911019999985001, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00234404599990512, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003566974000079881, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003566974000079881 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.011122505000230376, |
|
"count": 6, |
|
"is_parallel": true, |
|
"self": 0.0018661929996142135, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.009256312000616163, |
|
"count": 24, |
|
"is_parallel": true, |
|
"self": 0.009256312000616163 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 662.4245765729675, |
|
"count": 31773, |
|
"is_parallel": true, |
|
"self": 40.155766980000635, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 20.78963876998432, |
|
"count": 31773, |
|
"is_parallel": true, |
|
"self": 20.78963876998432 |
|
}, |
|
"communicator.exchange": { |
|
"total": 472.86539670498286, |
|
"count": 31773, |
|
"is_parallel": true, |
|
"self": 472.86539670498286 |
|
}, |
|
"steps_from_proto": { |
|
"total": 128.6137741179997, |
|
"count": 63546, |
|
"is_parallel": true, |
|
"self": 22.407620258942643, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 106.20615385905705, |
|
"count": 254184, |
|
"is_parallel": true, |
|
"self": 106.20615385905705 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 735.8517881820139, |
|
"count": 31774, |
|
"self": 7.557935876023976, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 150.53404438198953, |
|
"count": 31774, |
|
"self": 150.53404438198953 |
|
}, |
|
"_update_policy": { |
|
"total": 577.7598079240004, |
|
"count": 21, |
|
"self": 107.79722011599904, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 469.96258780800133, |
|
"count": 630, |
|
"self": 469.96258780800133 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.610000026630587e-06, |
|
"count": 1, |
|
"self": 1.610000026630587e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.48446938500001124, |
|
"count": 1, |
|
"self": 0.0020487920000960003, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.48242059299991524, |
|
"count": 1, |
|
"self": 0.48242059299991524 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |