{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4621256589889526, "min": 1.280769944190979, "max": 3.2957427501678467, "count": 4999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25967.3515625, "min": 18617.486328125, "max": 155810.875, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.58461538461539, "min": 38.80952380952381, "max": 999.0, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19132.0, "min": 11988.0, "max": 31968.0, "count": 4999 }, "SoccerTwos.Step.mean": { "value": 49999950.0, "min": 9000.0, "max": 49999950.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999950.0, "min": 9000.0, "max": 49999950.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008677976205945015, "min": -0.1454649567604065, "max": 0.20084896683692932, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.1281368732452393, "min": -29.965782165527344, "max": 29.345890045166016, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010827634483575821, "min": -0.14905725419521332, "max": 0.20505879819393158, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.407592535018921, "min": -30.705793380737305, "max": 29.85542869567871, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1060953873854417, "min": -0.8461538461538461, "max": 0.5513454499569806, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.792400360107422, "min": -70.87159997224808, "max": 58.947200298309326, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1060953873854417, "min": -0.8461538461538461, "max": 0.5513454499569806, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.792400360107422, "min": -70.87159997224808, "max": 58.947200298309326, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1698.3334663362982, "min": 1180.150765225715, "max": 1785.6079146689585, "count": 4805 }, "SoccerTwos.Self-play.ELO.sum": { "value": 220783.35062371875, "min": 2360.30153045143, "max": 435539.1608671374, "count": 4805 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02196764590917155, "min": 0.009764704160382583, "max": 0.025433018419425933, "count": 2413 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02196764590917155, "min": 0.009764704160382583, "max": 0.025433018419425933, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09797533204158147, "min": 3.4607449883594656e-08, "max": 0.12879207953810692, "count": 2413 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09797533204158147, "min": 3.4607449883594656e-08, "max": 0.12879207953810692, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09918076793352763, "min": 7.535348440039039e-08, "max": 0.12992177282770476, "count": 2413 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09918076793352763, "min": 7.535348440039039e-08, "max": 0.12992177282770476, "count": 2413 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2413 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2413 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2413 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731240825", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env ./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731285865" }, "total": 45039.967324682, "count": 1, "self": 0.16651835999800824, "children": { "run_training.setup": { "total": 0.008755893999477848, "count": 1, "self": 0.008755893999477848 }, "TrainerController.start_learning": { "total": 45039.792050428005, "count": 1, "self": 56.04159170886851, "children": { "TrainerController._reset_env": { "total": 7.723141937996843, "count": 250, "self": 7.723141937996843 }, "TrainerController.advance": { "total": 44975.63950396014, "count": 3431775, "self": 57.57684400135622, "children": { "env_step": { "total": 34017.37396647387, "count": 3431775, "self": 24313.65534247293, "children": { "SubprocessEnvManager._take_step": { "total": 9669.041964306514, "count": 3431775, "self": 285.4312219972089, "children": { "TorchPolicy.evaluate": { "total": 9383.610742309305, "count": 6299362, "self": 9383.610742309305 } } }, "workers": { "total": 34.67665969442169, "count": 3431775, "self": 0.0, "children": { "worker_root": { "total": 44959.616609847806, "count": 3431775, "is_parallel": true, "self": 25686.76858050111, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.029977671001688577, "count": 2, "is_parallel": true, "self": 0.028926475999469403, "children": { "_process_rank_one_or_two_observation": { "total": 0.001051195002219174, "count": 8, "is_parallel": true, "self": 0.001051195002219174 } } }, "UnityEnvironment.step": { "total": 0.012011115002678707, "count": 1, "is_parallel": true, "self": 0.00027799800227512605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021334000120987184, "count": 1, "is_parallel": true, "self": 0.00021334000120987184 }, "communicator.exchange": { "total": 0.010756171999673825, "count": 1, "is_parallel": true, "self": 0.010756171999673825 }, "steps_from_proto": { "total": 0.0007636049995198846, "count": 2, "is_parallel": true, "self": 0.00015008800619398244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006135169933259021, "count": 8, "is_parallel": true, "self": 0.0006135169933259021 } } } } } } }, "UnityEnvironment.step": { "total": 19272.63218522768, "count": 3431774, "is_parallel": true, "self": 997.7300711314856, "children": { "UnityEnvironment._generate_step_input": { "total": 612.1265179692346, "count": 3431774, "is_parallel": true, "self": 612.1265179692346 }, "communicator.exchange": { "total": 14875.540548649002, "count": 3431774, "is_parallel": true, "self": 14875.540548649002 }, "steps_from_proto": { "total": 2787.2350474779596, "count": 6863548, "is_parallel": true, "self": 545.6683956978122, "children": { "_process_rank_one_or_two_observation": { "total": 2241.5666517801474, "count": 27454192, "is_parallel": true, "self": 2241.5666517801474 } } } } }, "steps_from_proto": { "total": 0.21584411901494605, "count": 498, "is_parallel": true, "self": 0.044062083903554594, "children": { "_process_rank_one_or_two_observation": { "total": 0.17178203511139145, "count": 1992, "is_parallel": true, "self": 0.17178203511139145 } } } } } } } } }, "trainer_advance": { "total": 10900.68869348492, "count": 3431775, "self": 425.6903976532012, "children": { "process_trajectory": { "total": 4838.4257322837075, "count": 3431775, "self": 4801.599955648708, "children": { "RLTrainer._checkpoint": { "total": 36.825776634999784, "count": 100, "self": 36.825776634999784 } } }, "_update_policy": { "total": 5636.572563548012, "count": 2413, "self": 3284.43296428525, "children": { "TorchPOCAOptimizer.update": { "total": 2352.139599262762, "count": 72402, "self": 2352.139599262762 } } } } } } }, "trainer_threads": { "total": 4.309986252337694e-07, "count": 1, "self": 4.309986252337694e-07 }, "TrainerController._save_models": { "total": 0.38781238999945344, "count": 1, "self": 0.0008202030003303662, "children": { "RLTrainer._checkpoint": { "total": 0.3869921869991231, "count": 1, "self": 0.3869921869991231 } } } } } } }