|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.93532133102417, |
|
"min": 1.9228694438934326, |
|
"max": 3.2956340312957764, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 37901.33203125, |
|
"min": 15953.810546875, |
|
"max": 121993.4375, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 57.6551724137931, |
|
"min": 45.728971962616825, |
|
"max": 999.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 20064.0, |
|
"min": 16388.0, |
|
"max": 24572.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1570.3648351101099, |
|
"min": 1183.4809839587417, |
|
"max": 1579.7124319617544, |
|
"count": 462 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 273243.48130915913, |
|
"min": 2368.01158658732, |
|
"max": 322791.4845244262, |
|
"count": 462 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 4999965.0, |
|
"min": 9310.0, |
|
"max": 4999965.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 4999965.0, |
|
"min": 9310.0, |
|
"max": 4999965.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.05254178121685982, |
|
"min": -0.06817479431629181, |
|
"max": 0.25315922498703003, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 9.1422700881958, |
|
"min": -11.19851303100586, |
|
"max": 27.594356536865234, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.05239120498299599, |
|
"min": -0.06603290885686874, |
|
"max": 0.24999599158763885, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 9.116069793701172, |
|
"min": -12.472119331359863, |
|
"max": 27.249563217163086, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.027245977144131715, |
|
"min": -0.8125, |
|
"max": 0.5217555546098285, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 4.7408000230789185, |
|
"min": -43.884000182151794, |
|
"max": 52.70480006933212, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.027245977144131715, |
|
"min": -0.8125, |
|
"max": 0.5217555546098285, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 4.7408000230789185, |
|
"min": -43.884000182151794, |
|
"max": 52.70480006933212, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.019540009875587808, |
|
"min": 0.011188588462149103, |
|
"max": 0.023791296190271774, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.019540009875587808, |
|
"min": 0.011188588462149103, |
|
"max": 0.023791296190271774, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10733787094553311, |
|
"min": 2.080253307212843e-06, |
|
"max": 0.11480278223752975, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10733787094553311, |
|
"min": 2.080253307212843e-06, |
|
"max": 0.11480278223752975, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.10846167479952176, |
|
"min": 1.9527220464018075e-06, |
|
"max": 0.11766273006796837, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.10846167479952176, |
|
"min": 1.9527220464018075e-06, |
|
"max": 0.11766273006796837, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 239 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 239 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1681122148", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/home/sicong/Data/Projects/HuggingFace_DeepReinforcementLearning/venv_shared/bin/mlagents-learn ./SoccerTwos.yaml --env=./training-envs-executables/linux/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": "1681127823" |
|
}, |
|
"total": 5674.665851216007, |
|
"count": 1, |
|
"self": 0.1807679940102389, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.12766640599875245, |
|
"count": 1, |
|
"self": 0.12766640599875245 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 5674.357416815998, |
|
"count": 1, |
|
"self": 4.425807208011975, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.309263809991535, |
|
"count": 20, |
|
"self": 3.309263809991535 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 5666.350771254991, |
|
"count": 336237, |
|
"self": 4.078188825093093, |
|
"children": { |
|
"env_step": { |
|
"total": 4206.0092518964375, |
|
"count": 336237, |
|
"self": 3256.9958848187525, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 946.5169658295636, |
|
"count": 336237, |
|
"self": 26.451491816114867, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 920.0654740134487, |
|
"count": 632474, |
|
"self": 920.0654740134487 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.4964012481214013, |
|
"count": 336237, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 5667.749886682577, |
|
"count": 336237, |
|
"is_parallel": true, |
|
"self": 2959.9660778657417, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001744405017234385, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0003522140032146126, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013921910140197724, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013921910140197724 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.01870985199639108, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006707470020046458, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004609339957823977, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004609339957823977 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.016097498999442905, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.016097498999442905 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0014806719991611317, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00024401101109106094, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012366609880700707, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012366609880700707 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2707.7565631848265, |
|
"count": 336236, |
|
"is_parallel": true, |
|
"self": 200.43624722062668, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 124.41545320049045, |
|
"count": 336236, |
|
"is_parallel": true, |
|
"self": 124.41545320049045 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1927.032509234923, |
|
"count": 336236, |
|
"is_parallel": true, |
|
"self": 1927.032509234923 |
|
}, |
|
"steps_from_proto": { |
|
"total": 455.87235352878633, |
|
"count": 672472, |
|
"is_parallel": true, |
|
"self": 71.89859090356913, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 383.9737626252172, |
|
"count": 2689888, |
|
"is_parallel": true, |
|
"self": 383.9737626252172 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.027245632008998655, |
|
"count": 38, |
|
"is_parallel": true, |
|
"self": 0.0043746480223489925, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.022870983986649662, |
|
"count": 152, |
|
"is_parallel": true, |
|
"self": 0.022870983986649662 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1456.2633305334602, |
|
"count": 336237, |
|
"self": 39.944305689728935, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 479.6868951536162, |
|
"count": 336237, |
|
"self": 476.6264334236039, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 3.060461730012321, |
|
"count": 10, |
|
"self": 3.060461730012321 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 936.6321296901151, |
|
"count": 239, |
|
"self": 592.2271633920609, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 344.4049662980542, |
|
"count": 7170, |
|
"self": 344.4049662980542 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.899928510189056e-07, |
|
"count": 1, |
|
"self": 5.899928510189056e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2715739530103747, |
|
"count": 1, |
|
"self": 0.000999018011498265, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2705749349988764, |
|
"count": 1, |
|
"self": 0.2705749349988764 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |