{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5180116891860962, "min": 1.4454188346862793, "max": 3.29571533203125, "count": 2221 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30457.38671875, "min": 17305.02734375, "max": 105462.890625, "count": 2221 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.372093023255815, "min": 39.900826446280995, "max": 999.0, "count": 2221 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19736.0, "min": 2100.0, "max": 30648.0, "count": 2221 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1722.349706373526, "min": 1198.250783323078, "max": 1745.8182709345028, "count": 2216 }, "SoccerTwos.Self-play.ELO.sum": { "value": 296244.1494962465, "min": 2396.501566646156, "max": 405778.00482238666, "count": 2216 }, "SoccerTwos.Step.mean": { "value": 22209973.0, "min": 9336.0, "max": 22209973.0, "count": 2221 }, "SoccerTwos.Step.sum": { "value": 22209973.0, "min": 9336.0, "max": 22209973.0, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03428282588720322, "min": -0.14800982177257538, "max": 0.2558770477771759, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.896646022796631, "min": -27.825847625732422, "max": 40.964725494384766, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03643205761909485, "min": -0.14976127445697784, "max": 0.26182278990745544, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.2663140296936035, "min": -28.155120849609375, "max": 40.79194641113281, "count": 2221 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2221 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.060987208125203154, "min": -0.5384615384615384, "max": 0.5767752509756187, "count": 2221 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -10.489799797534943, "min": -62.88960003852844, "max": 87.52079963684082, "count": 2221 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.060987208125203154, "min": -0.5384615384615384, "max": 0.5767752509756187, "count": 2221 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -10.489799797534943, "min": -62.88960003852844, "max": 87.52079963684082, "count": 2221 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2221 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2221 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015303168269262339, "min": 0.00969520800281316, "max": 0.025596016241858404, "count": 1076 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015303168269262339, "min": 0.00969520800281316, "max": 0.025596016241858404, "count": 1076 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09073079278071722, "min": 0.000485869481053669, "max": 0.12644617433349292, "count": 1076 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09073079278071722, "min": 0.000485869481053669, "max": 0.12644617433349292, "count": 1076 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09238106608390809, "min": 0.0004703054859419353, "max": 0.12909239009022713, "count": 1076 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09238106608390809, "min": 0.0004703054859419353, "max": 0.12909239009022713, "count": 1076 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1076 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1076 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1076 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1076 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1076 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1076 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691990937", "python_version": "3.9.17 (main, Jun 6 2023, 14:51:25) \n[Clang 14.0.0 (clang-1400.0.29.202)]", "command_line_arguments": "/opt/homebrew/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1692089480" }, "total": 87773.452843291, "count": 1, "self": 0.29323479101003613, "children": { "run_training.setup": { "total": 0.012931833000000004, "count": 1, "self": 0.012931833000000004 }, "TrainerController.start_learning": { "total": 87773.14667666699, "count": 1, "self": 18.52444173611002, "children": { "TrainerController._reset_env": { "total": 5.2202975420258495, "count": 45, "self": 5.2202975420258495 }, "TrainerController.advance": { "total": 87749.29852159687, "count": 1536643, "self": 15.261688980754116, "children": { "env_step": { "total": 70728.52475216024, "count": 1536643, "self": 68498.25063299523, "children": { "SubprocessEnvManager._take_step": { "total": 2217.9738781351307, "count": 1536643, "self": 67.96943288873308, "children": { "TorchPolicy.evaluate": { "total": 2150.0044452463976, "count": 2782144, "self": 2150.0044452463976 } } }, "workers": { "total": 12.300241029887857, "count": 1536642, "self": 0.0, "children": { "worker_root": { "total": 87740.17694592892, "count": 1536642, "is_parallel": true, "self": 21206.658549477477, "children": { "steps_from_proto": { "total": 0.05824782700782105, "count": 90, "is_parallel": true, "self": 0.008160852064073243, "children": { "_process_rank_one_or_two_observation": { "total": 0.05008697494374781, "count": 360, "is_parallel": true, "self": 0.05008697494374781 } } }, "UnityEnvironment.step": { "total": 66533.46014862444, "count": 1536642, "is_parallel": true, "self": 186.54595784033882, "children": { "UnityEnvironment._generate_step_input": { "total": 1097.6344130796806, "count": 1536642, "is_parallel": true, "self": 1097.6344130796806 }, "communicator.exchange": { "total": 63139.39043407236, "count": 1536642, "is_parallel": true, "self": 63139.39043407236 }, "steps_from_proto": { "total": 2109.8893436320604, "count": 3073284, "is_parallel": true, "self": 289.05307752988233, "children": { "_process_rank_one_or_two_observation": { "total": 1820.8362661021781, "count": 12293136, "is_parallel": true, "self": 1820.8362661021781 } } } } } } } } } } }, "trainer_advance": { "total": 17005.51208045587, "count": 1536642, "self": 129.9304254619965, "children": { "process_trajectory": { "total": 3454.6522683280746, "count": 1536642, "self": 3450.1358742450866, "children": { "RLTrainer._checkpoint": { "total": 4.516394082987745, "count": 44, "self": 4.516394082987745 } } }, "_update_policy": { "total": 13420.929386665797, "count": 1077, "self": 1779.8083239908337, "children": { "TorchPOCAOptimizer.update": { "total": 11641.121062674963, "count": 32322, "self": 11641.121062674963 } } } } } } }, "trainer_threads": { "total": 4.999892553314567e-07, "count": 1, "self": 4.999892553314567e-07 }, "TrainerController._save_models": { "total": 0.10341529200377408, "count": 1, "self": 0.002299376006703824, "children": { "RLTrainer._checkpoint": { "total": 0.10111591599707026, "count": 1, "self": 0.10111591599707026 } } } } } } }