{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8880484104156494, "min": 1.8722083568572998, "max": 3.295706272125244, "count": 658 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37640.1328125, "min": 16156.5458984375, "max": 129450.4296875, "count": 658 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.350515463917525, "min": 43.8018018018018, "max": 999.0, "count": 658 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19924.0, "min": 12552.0, "max": 27672.0, "count": 658 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1569.4211476285388, "min": 1193.541211126307, "max": 1603.5013753562646, "count": 629 }, "SoccerTwos.Self-play.ELO.sum": { "value": 304467.7026399365, "min": 2393.0391837766865, "max": 346934.84204839927, "count": 629 }, "SoccerTwos.Step.mean": { "value": 6579974.0, "min": 9852.0, "max": 6579974.0, "count": 658 }, "SoccerTwos.Step.sum": { "value": 6579974.0, "min": 9852.0, "max": 6579974.0, "count": 658 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00906392838805914, "min": -0.10840822756290436, "max": 0.1630936861038208, "count": 658 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.749338150024414, "min": -22.00687026977539, "max": 32.29254913330078, "count": 658 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009686826728284359, "min": -0.10873053967952728, "max": 0.16325582563877106, "count": 658 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.869557499885559, "min": -22.07229995727539, "max": 32.32465362548828, "count": 658 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 658 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 658 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07653367581145133, "min": -0.6875, "max": 0.46086666981379193, "count": 658 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 14.770999431610107, "min": -49.34479993581772, "max": 48.02979975938797, "count": 658 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07653367581145133, "min": -0.6875, "max": 0.46086666981379193, "count": 658 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 14.770999431610107, "min": -49.34479993581772, "max": 48.02979975938797, "count": 658 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 658 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 658 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01758310463167921, "min": 0.010413085353987602, "max": 0.023296837213759622, "count": 313 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01758310463167921, "min": 0.010413085353987602, "max": 0.023296837213759622, "count": 313 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11528517901897431, "min": 4.9890405837989725e-05, "max": 0.12334234490990639, "count": 313 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11528517901897431, "min": 4.9890405837989725e-05, "max": 0.12334234490990639, "count": 313 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11799983779589335, "min": 4.931844996463042e-05, "max": 0.1262499362230301, "count": 313 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11799983779589335, "min": 4.931844996463042e-05, "max": 0.1262499362230301, "count": 313 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 313 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 313 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 313 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 313 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 313 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 313 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683547966", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/jovisaib/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos --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", "numpy_version": "1.21.2", "end_time_seconds": "1683573486" }, "total": 25519.760386834, "count": 1, "self": 0.21833533400058514, "children": { "run_training.setup": { "total": 0.08148787500000054, "count": 1, "self": 0.08148787500000054 }, "TrainerController.start_learning": { "total": 25519.460563625, "count": 1, "self": 4.096770783682587, "children": { "TrainerController._reset_env": { "total": 2.912471209002332, "count": 33, "self": 2.912471209002332 }, "TrainerController.advance": { "total": 25512.368457882316, "count": 441051, "self": 4.251637718884012, "children": { "env_step": { "total": 20981.41589841332, "count": 441051, "self": 20308.931328215007, "children": { "SubprocessEnvManager._take_step": { "total": 669.0785221537078, "count": 441051, "self": 19.03499032753257, "children": { "TorchPolicy.evaluate": { "total": 650.0435318261752, "count": 837704, "self": 650.0435318261752 } } }, "workers": { "total": 3.4060480446074965, "count": 441050, "self": 0.0, "children": { "worker_root": { "total": 25509.549095601204, "count": 441050, "is_parallel": true, "self": 5781.137212207312, "children": { "steps_from_proto": { "total": 0.04613553898625544, "count": 66, "is_parallel": true, "self": 0.0054039940053833835, "children": { "_process_rank_one_or_two_observation": { "total": 0.04073154498087206, "count": 264, "is_parallel": true, "self": 0.04073154498087206 } } }, "UnityEnvironment.step": { "total": 19728.365747854907, "count": 441050, "is_parallel": true, "self": 53.23034296190235, "children": { "UnityEnvironment._generate_step_input": { "total": 352.1141099562241, "count": 441050, "is_parallel": true, "self": 352.1141099562241 }, "communicator.exchange": { "total": 18574.619126274312, "count": 441050, "is_parallel": true, "self": 18574.619126274312 }, "steps_from_proto": { "total": 748.4021686624687, "count": 882100, "is_parallel": true, "self": 80.83071414853873, "children": { "_process_rank_one_or_two_observation": { "total": 667.57145451393, "count": 3528400, "is_parallel": true, "self": 667.57145451393 } } } } } } } } } } }, "trainer_advance": { "total": 4526.70092175011, "count": 441050, "self": 35.48097765252987, "children": { "process_trajectory": { "total": 830.5695127995796, "count": 441050, "self": 829.5063930085789, "children": { "RLTrainer._checkpoint": { "total": 1.063119791000645, "count": 13, "self": 1.063119791000645 } } }, "_update_policy": { "total": 3660.6504312980005, "count": 313, "self": 423.46463323612033, "children": { "TorchPOCAOptimizer.update": { "total": 3237.18579806188, "count": 9393, "self": 3237.18579806188 } } } } } } }, "trainer_threads": { "total": 7.920025382190943e-07, "count": 1, "self": 7.920025382190943e-07 }, "TrainerController._save_models": { "total": 0.08286295799916843, "count": 1, "self": 0.0011063329984608572, "children": { "RLTrainer._checkpoint": { "total": 0.08175662500070757, "count": 1, "self": 0.08175662500070757 } } } } } } }