{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.034095048904419, "min": 2.034095048904419, "max": 3.2957186698913574, "count": 506 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43415.7265625, "min": 21021.2265625, "max": 136054.640625, "count": 506 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.92857142857143, "min": 43.642857142857146, "max": 999.0, "count": 506 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19464.0, "min": 13476.0, "max": 28232.0, "count": 506 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1444.277444267153, "min": 1188.5688610622024, "max": 1467.9057905021382, "count": 459 }, "SoccerTwos.Self-play.ELO.sum": { "value": 242638.6106368817, "min": 2378.6217784244172, "max": 318196.4601373692, "count": 459 }, "SoccerTwos.Step.mean": { "value": 5059920.0, "min": 9138.0, "max": 5059920.0, "count": 506 }, "SoccerTwos.Step.sum": { "value": 5059920.0, "min": 9138.0, "max": 5059920.0, "count": 506 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.008102988824248314, "min": -0.102271169424057, "max": 0.15609072148799896, "count": 506 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.3694051504135132, "min": -15.033862113952637, "max": 27.724905014038086, "count": 506 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0010254208464175463, "min": -0.10244327783584595, "max": 0.15248753130435944, "count": 506 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.17329612374305725, "min": -15.059162139892578, "max": 26.837806701660156, "count": 506 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 506 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 506 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04445562172218187, "min": -0.6912857123783657, "max": 0.34533906215801835, "count": 506 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 7.513000071048737, "min": -55.49279975891113, "max": 59.57000023126602, "count": 506 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04445562172218187, "min": -0.6912857123783657, "max": 0.34533906215801835, "count": 506 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 7.513000071048737, "min": -55.49279975891113, "max": 59.57000023126602, "count": 506 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 506 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 506 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015287019886697333, "min": 0.011718268912348624, "max": 0.02362056450607876, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015287019886697333, "min": 0.011718268912348624, "max": 0.02362056450607876, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08906070366501809, "min": 1.4289946382935645e-06, "max": 0.10702010343472163, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08906070366501809, "min": 1.4289946382935645e-06, "max": 0.10702010343472163, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09028938934206962, "min": 1.5878587040181932e-06, "max": 0.11088861897587776, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09028938934206962, "min": 1.5878587040181932e-06, "max": 0.11088861897587776, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710034452", "python_version": "3.10.12 (main, Mar 9 2024, 16:10:11) [Clang 14.0.3 (clang-1403.0.22.14.1)]", "command_line_arguments": "/Users/rushideshmukh/.pyenv/versions/3.10.12/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1", "numpy_version": "1.23.5", "end_time_seconds": "1710053756" }, "total": 19304.27785824999, "count": 1, "self": 0.33178508398123085, "children": { "run_training.setup": { "total": 0.016164916014531627, "count": 1, "self": 0.016164916014531627 }, "TrainerController.start_learning": { "total": 19303.929908249993, "count": 1, "self": 2.9813993361894973, "children": { "TrainerController._reset_env": { "total": 5.200544664054178, "count": 26, "self": 5.200544664054178 }, "TrainerController.advance": { "total": 19295.492771041783, "count": 339291, "self": 2.7193128646176774, "children": { "env_step": { "total": 15219.818307881098, "count": 339291, "self": 14713.968574603234, "children": { "SubprocessEnvManager._take_step": { "total": 503.8066189119709, "count": 339291, "self": 14.768715203303145, "children": { "TorchPolicy.evaluate": { "total": 489.0379037086677, "count": 644640, "self": 489.0379037086677 } } }, "workers": { "total": 2.043114365893416, "count": 339290, "self": 0.0, "children": { "worker_root": { "total": 19295.864006676624, "count": 339290, "is_parallel": true, "self": 5003.252988209628, "children": { "steps_from_proto": { "total": 0.042950455099344254, "count": 52, "is_parallel": true, "self": 0.005378327245125547, "children": { "_process_rank_one_or_two_observation": { "total": 0.037572127854218706, "count": 208, "is_parallel": true, "self": 0.037572127854218706 } } }, "UnityEnvironment.step": { "total": 14292.568068011897, "count": 339290, "is_parallel": true, "self": 35.37599831694388, "children": { "UnityEnvironment._generate_step_input": { "total": 256.56465872059925, "count": 339290, "is_parallel": true, "self": 256.56465872059925 }, "communicator.exchange": { "total": 13514.89062661829, "count": 339290, "is_parallel": true, "self": 13514.89062661829 }, "steps_from_proto": { "total": 485.73678435606416, "count": 678580, "is_parallel": true, "self": 55.636882274993695, "children": { "_process_rank_one_or_two_observation": { "total": 430.09990208107047, "count": 2714320, "is_parallel": true, "self": 430.09990208107047 } } } } } } } } } } }, "trainer_advance": { "total": 4072.9551502960676, "count": 339290, "self": 33.577861527737696, "children": { "process_trajectory": { "total": 621.0739785193873, "count": 339290, "self": 619.0081556433288, "children": { "RLTrainer._checkpoint": { "total": 2.065822876058519, "count": 10, "self": 2.065822876058519 } } }, "_update_policy": { "total": 3418.3033102489426, "count": 241, "self": 385.8818468901736, "children": { "TorchPOCAOptimizer.update": { "total": 3032.421463358769, "count": 7230, "self": 3032.421463358769 } } } } } } }, "trainer_threads": { "total": 1.2499804142862558e-06, "count": 1, "self": 1.2499804142862558e-06 }, "TrainerController._save_models": { "total": 0.25519195798551664, "count": 1, "self": 0.0014662499888800085, "children": { "RLTrainer._checkpoint": { "total": 0.25372570799663663, "count": 1, "self": 0.25372570799663663 } } } } } } }