{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8076962232589722, "min": 1.7819339036941528, "max": 3.262948751449585, "count": 475 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36963.7734375, "min": 19207.3046875, "max": 116619.453125, "count": 475 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.94117647058823, "min": 42.64035087719298, "max": 999.0, "count": 475 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19700.0, "min": 6844.0, "max": 29536.0, "count": 475 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1534.9474694701007, "min": 1201.9389321995466, "max": 1547.3432578079767, "count": 439 }, "SoccerTwos.Self-play.ELO.sum": { "value": 260941.06980991713, "min": 2407.69789629098, "max": 338478.536966551, "count": 439 }, "SoccerTwos.Step.mean": { "value": 4999976.0, "min": 259303.0, "max": 4999976.0, "count": 475 }, "SoccerTwos.Step.sum": { "value": 4999976.0, "min": 259303.0, "max": 4999976.0, "count": 475 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012712719850242138, "min": -0.14976486563682556, "max": 0.20277804136276245, "count": 475 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.1611623764038086, "min": -28.334848403930664, "max": 24.135982513427734, "count": 475 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02103506028652191, "min": -0.15318411588668823, "max": 0.19561652839183807, "count": 475 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.575960159301758, "min": -28.89899444580078, "max": 24.811716079711914, "count": 475 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 475 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 475 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.01902353272718542, "min": -0.5, "max": 0.38864348504854285, "count": 475 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.234000563621521, "min": -54.75440001487732, "max": 55.22799926996231, "count": 475 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01902353272718542, "min": -0.5, "max": 0.38864348504854285, "count": 475 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.234000563621521, "min": -54.75440001487732, "max": 55.22799926996231, "count": 475 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 475 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 475 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01658453510705537, "min": 0.011250831291545183, "max": 0.024212790377593288, "count": 227 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01658453510705537, "min": 0.011250831291545183, "max": 0.024212790377593288, "count": 227 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10030790815750758, "min": 8.970231732519097e-07, "max": 0.11408859317501387, "count": 227 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10030790815750758, "min": 8.970231732519097e-07, "max": 0.11408859317501387, "count": 227 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10285816689332326, "min": 1.0710856846192958e-06, "max": 0.11636602307359377, "count": 227 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10285816689332326, "min": 1.0710856846192958e-06, "max": 0.11636602307359377, "count": 227 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 227 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 227 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 227 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 227 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 227 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 227 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724991449", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/home/ree/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos-v1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1725013720" }, "total": 22271.048418547027, "count": 1, "self": 1.6572192239109427, "children": { "run_training.setup": { "total": 0.05296880006790161, "count": 1, "self": 0.05296880006790161 }, "TrainerController.start_learning": { "total": 22269.338230523048, "count": 1, "self": 11.081928212777711, "children": { "TrainerController._reset_env": { "total": 8.206955909729004, "count": 25, "self": 8.206955909729004 }, "TrainerController.advance": { "total": 22246.67521870148, "count": 322651, "self": 12.121655223309062, "children": { "env_step": { "total": 13591.52774995612, "count": 322651, "self": 7520.536932082265, "children": { "SubprocessEnvManager._take_step": { "total": 6064.714331688825, "count": 322651, "self": 87.30673468415625, "children": { "TorchPolicy.evaluate": { "total": 5977.407597004669, "count": 598628, "self": 5977.407597004669 } } }, "workers": { "total": 6.27648618503008, "count": 322651, "self": 0.0, "children": { "worker_root": { "total": 22233.72680687369, "count": 322651, "is_parallel": true, "self": 15979.07816945517, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006125499960035086, "count": 2, "is_parallel": true, "self": 0.001506500062532723, "children": { "_process_rank_one_or_two_observation": { "total": 0.004618999897502363, "count": 8, "is_parallel": true, "self": 0.004618999897502363 } } }, "UnityEnvironment.step": { "total": 0.05540189903695136, "count": 1, "is_parallel": true, "self": 0.0010332000674679875, "children": { "UnityEnvironment._generate_step_input": { "total": 0.001042800024151802, "count": 1, "is_parallel": true, "self": 0.001042800024151802 }, "communicator.exchange": { "total": 0.050675099017098546, "count": 1, "is_parallel": true, "self": 0.050675099017098546 }, "steps_from_proto": { "total": 0.0026507999282330275, "count": 2, "is_parallel": true, "self": 0.0006300997920334339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020207001361995935, "count": 8, "is_parallel": true, "self": 0.0020207001361995935 } } } } } } }, "steps_from_proto": { "total": 0.06163759820628911, "count": 48, "is_parallel": true, "self": 0.013903398532420397, "children": { "_process_rank_one_or_two_observation": { "total": 0.047734199673868716, "count": 192, "is_parallel": true, "self": 0.047734199673868716 } } }, "UnityEnvironment.step": { "total": 6254.5869998203125, "count": 322650, "is_parallel": true, "self": 340.37889847927727, "children": { "UnityEnvironment._generate_step_input": { "total": 208.21101368858945, "count": 322650, "is_parallel": true, "self": 208.21101368858945 }, "communicator.exchange": { "total": 4663.439850871218, "count": 322650, "is_parallel": true, "self": 4663.439850871218 }, "steps_from_proto": { "total": 1042.5572367812274, "count": 645300, "is_parallel": true, "self": 228.82331389945466, "children": { "_process_rank_one_or_two_observation": { "total": 813.7339228817727, "count": 2581200, "is_parallel": true, "self": 813.7339228817727 } } } } } } } } } } }, "trainer_advance": { "total": 8643.02581352205, "count": 322651, "self": 66.703303639777, "children": { "process_trajectory": { "total": 2746.8216791017912, "count": 322651, "self": 2738.176675839699, "children": { "RLTrainer._checkpoint": { "total": 8.64500326209236, "count": 10, "self": 8.64500326209236 } } }, "_update_policy": { "total": 5829.500830780482, "count": 227, "self": 877.3318114578724, "children": { "TorchPOCAOptimizer.update": { "total": 4952.1690193226095, "count": 6828, "self": 4952.1690193226095 } } } } } } }, "trainer_threads": { "total": 1.300009898841381e-06, "count": 1, "self": 1.300009898841381e-06 }, "TrainerController._save_models": { "total": 3.3741263990523294, "count": 1, "self": 0.13813989306800067, "children": { "RLTrainer._checkpoint": { "total": 3.2359865059843287, "count": 1, "self": 3.2359865059843287 } } } } } } }