| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.7180193662643433, | |
| "min": 1.7169474363327026, | |
| "max": 3.2957441806793213, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 34690.24609375, | |
| "min": 16131.07421875, | |
| "max": 140922.515625, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 66.06666666666666, | |
| "min": 41.61538461538461, | |
| "max": 999.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19820.0, | |
| "min": 13584.0, | |
| "max": 28736.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1625.8410519662657, | |
| "min": 1185.8544299297316, | |
| "max": 1631.4416858275144, | |
| "count": 750 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 243876.15779493985, | |
| "min": 2373.431629846521, | |
| "max": 358590.00508752686, | |
| "count": 750 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 7869994.0, | |
| "min": 9384.0, | |
| "max": 7869994.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 7869994.0, | |
| "min": 9384.0, | |
| "max": 7869994.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.009102094918489456, | |
| "min": -0.11238310486078262, | |
| "max": 0.17347067594528198, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 1.365314245223999, | |
| "min": -20.116575241088867, | |
| "max": 21.37743377685547, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.0034246540162712336, | |
| "min": -0.10482959449291229, | |
| "max": 0.17781499028205872, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 0.5136981010437012, | |
| "min": -19.634157180786133, | |
| "max": 21.74544334411621, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.011397332350413004, | |
| "min": -0.7266000015395028, | |
| "max": 0.4861166576544444, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -1.7095998525619507, | |
| "min": -49.8672000169754, | |
| "max": 56.26180016994476, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.011397332350413004, | |
| "min": -0.7266000015395028, | |
| "max": 0.4861166576544444, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -1.7095998525619507, | |
| "min": -49.8672000169754, | |
| "max": 56.26180016994476, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 787 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01732818890401783, | |
| "min": 0.009920780318013082, | |
| "max": 0.0233591943862848, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01732818890401783, | |
| "min": 0.009920780318013082, | |
| "max": 0.0233591943862848, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.09881145680944124, | |
| "min": 1.6208294994157769e-06, | |
| "max": 0.11842111423611641, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.09881145680944124, | |
| "min": 1.6208294994157769e-06, | |
| "max": 0.11842111423611641, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.10014958679676056, | |
| "min": 1.6126407217598172e-06, | |
| "max": 0.12048137858510018, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.10014958679676056, | |
| "min": 1.6126407217598172e-06, | |
| "max": 0.12048137858510018, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.2, | |
| "max": 0.20000000000000007, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.2, | |
| "max": 0.20000000000000007, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 377 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005, | |
| "max": 0.005000000000000001, | |
| "count": 377 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1679698174", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/home/yibo/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.10.2+cu111", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1679729109" | |
| }, | |
| "total": 30935.237442568, | |
| "count": 1, | |
| "self": 0.03809124100371264, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.010129379999852972, | |
| "count": 1, | |
| "self": 0.010129379999852972 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 30935.189221946996, | |
| "count": 1, | |
| "self": 8.493996333803807, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 5.343945046992303, | |
| "count": 40, | |
| "self": 5.343945046992303 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 30921.22087009319, | |
| "count": 535380, | |
| "self": 7.671441275608231, | |
| "children": { | |
| "env_step": { | |
| "total": 28878.602780573216, | |
| "count": 535380, | |
| "self": 27466.31712422939, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1407.5150980348299, | |
| "count": 535380, | |
| "self": 45.01167038467065, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1362.5034276501592, | |
| "count": 995452, | |
| "self": 1362.5034276501592 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 4.770558308993714, | |
| "count": 535379, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 30923.658859852934, | |
| "count": 535379, | |
| "is_parallel": true, | |
| "self": 4330.540863548518, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.001981433999389992, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00038393999784602784, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015974940015439643, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0015974940015439643 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05770361100076116, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00013167900215194095, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0009889229986583814, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0009889229986583814 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.054780389998995815, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.054780389998995815 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0018026190009550191, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0002745570018305443, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0015280619991244748, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0015280619991244748 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 26593.053648012406, | |
| "count": 535378, | |
| "is_parallel": true, | |
| "self": 68.33193406206192, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 508.81990166595824, | |
| "count": 535378, | |
| "is_parallel": true, | |
| "self": 508.81990166595824 | |
| }, | |
| "communicator.exchange": { | |
| "total": 25099.028850086477, | |
| "count": 535378, | |
| "is_parallel": true, | |
| "self": 25099.028850086477 | |
| }, | |
| "steps_from_proto": { | |
| "total": 916.872962197911, | |
| "count": 1070756, | |
| "is_parallel": true, | |
| "self": 125.42700791917923, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 791.4459542787317, | |
| "count": 4283024, | |
| "is_parallel": true, | |
| "self": 791.4459542787317 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.06434829200952663, | |
| "count": 78, | |
| "is_parallel": true, | |
| "self": 0.009044202002769453, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.05530409000675718, | |
| "count": 312, | |
| "is_parallel": true, | |
| "self": 0.05530409000675718 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 2034.9466482443659, | |
| "count": 535379, | |
| "self": 54.565092668593934, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 698.4577447428019, | |
| "count": 535379, | |
| "self": 696.5146503238138, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.9430944189880393, | |
| "count": 15, | |
| "self": 1.9430944189880393 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1281.92381083297, | |
| "count": 378, | |
| "self": 799.7250728169147, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 482.19873801605536, | |
| "count": 11343, | |
| "self": 482.19873801605536 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 7.730050128884614e-07, | |
| "count": 1, | |
| "self": 7.730050128884614e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.13040970000292873, | |
| "count": 1, | |
| "self": 0.0015894020034465939, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.12882029799948214, | |
| "count": 1, | |
| "self": 0.12882029799948214 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |