{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4069772958755493, "min": 1.3468372821807861, "max": 3.2957348823547363, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30075.546875, "min": 22171.5078125, "max": 105463.515625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.62337662337662, "min": 38.736, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18980.0, "min": 13080.0, "max": 28216.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1710.0113274282098, "min": 1196.073674877001, "max": 1772.7610341236173, "count": 4998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 263341.7444239443, "min": 2396.08127181869, "max": 419982.6893369895, "count": 4998 }, "SoccerTwos.Step.mean": { "value": 49999696.0, "min": 9128.0, "max": 49999696.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999696.0, "min": 9128.0, "max": 49999696.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.027086248621344566, "min": -0.13353946805000305, "max": 0.20947594940662384, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.2525410652160645, "min": -25.605226516723633, "max": 25.177820205688477, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02820216305553913, "min": -0.13313187658786774, "max": 0.20150870084762573, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.42773962020874, "min": -25.302413940429688, "max": 25.609683990478516, "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": 0.12298726352157106, "min": -0.5, "max": 0.46068000197410586, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.309000372886658, "min": -64.20120006799698, "max": 64.53359997272491, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.12298726352157106, "min": -0.5, "max": 0.46068000197410586, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.309000372886658, "min": -64.20120006799698, "max": 64.53359997272491, "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.Losses.PolicyLoss.mean": { "value": 0.017986779745357732, "min": 0.010510212313238298, "max": 0.02574000319194359, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017986779745357732, "min": 0.010510212313238298, "max": 0.02574000319194359, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07823928445577621, "min": 0.000528234158991836, "max": 0.13084790507952374, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07823928445577621, "min": 0.000528234158991836, "max": 0.13084790507952374, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07952647060155868, "min": 0.000523627806493702, "max": 0.1331552078326543, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07952647060155868, "min": 0.000523627806493702, "max": 0.1331552078326543, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696403757", "python_version": "3.9.18 (main, Sep 11 2023, 13:41:44) \n[GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos4 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0.dev20231003", "numpy_version": "1.26.0", "end_time_seconds": "1696473272" }, "total": 69514.93321041577, "count": 1, "self": 0.16795073170214891, "children": { "run_training.setup": { "total": 0.009656739421188831, "count": 1, "self": 0.009656739421188831 }, "TrainerController.start_learning": { "total": 69514.75560294464, "count": 1, "self": 37.14975555241108, "children": { "TrainerController._reset_env": { "total": 4.256752256304026, "count": 250, "self": 4.256752256304026 }, "TrainerController.advance": { "total": 69473.2781505268, "count": 3437367, "self": 32.72075719200075, "children": { "env_step": { "total": 35875.554074604996, "count": 3437367, "self": 31633.094030559063, "children": { "SubprocessEnvManager._take_step": { "total": 4219.770093231462, "count": 3437367, "self": 206.25313608534634, "children": { "TorchPolicy.evaluate": { "total": 4013.5169571461156, "count": 6279380, "self": 4013.5169571461156 } } }, "workers": { "total": 22.68995081447065, "count": 3437367, "self": 0.0, "children": { "worker_root": { "total": 69447.12859765999, "count": 3437367, "is_parallel": true, "self": 42521.725849598646, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002090802416205406, "count": 2, "is_parallel": true, "self": 0.0004257494583725929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016650529578328133, "count": 8, "is_parallel": true, "self": 0.0016650529578328133 } } }, "UnityEnvironment.step": { "total": 0.013848412781953812, "count": 1, "is_parallel": true, "self": 0.0003952775150537491, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002933889627456665, "count": 1, "is_parallel": true, "self": 0.0002933889627456665 }, "communicator.exchange": { "total": 0.012025302276015282, "count": 1, "is_parallel": true, "self": 0.012025302276015282 }, "steps_from_proto": { "total": 0.0011344440281391144, "count": 2, "is_parallel": true, "self": 0.00019432418048381805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009401198476552963, "count": 8, "is_parallel": true, "self": 0.0009401198476552963 } } } } } } }, "UnityEnvironment.step": { "total": 26925.02196652163, "count": 3437366, "is_parallel": true, "self": 1673.0620529102162, "children": { "UnityEnvironment._generate_step_input": { "total": 943.4379991926253, "count": 3437366, "is_parallel": true, "self": 943.4379991926253 }, "communicator.exchange": { "total": 19556.43012082018, "count": 3437366, "is_parallel": true, "self": 19556.43012082018 }, "steps_from_proto": { "total": 4752.091793598607, "count": 6874732, "is_parallel": true, "self": 799.6544350106269, "children": { "_process_rank_one_or_two_observation": { "total": 3952.4373585879803, "count": 27498928, "is_parallel": true, "self": 3952.4373585879803 } } } } }, "steps_from_proto": { "total": 0.3807815397158265, "count": 498, "is_parallel": true, "self": 0.06608195882290602, "children": { "_process_rank_one_or_two_observation": { "total": 0.3146995808929205, "count": 1992, "is_parallel": true, "self": 0.3146995808929205 } } } } } } } } }, "trainer_advance": { "total": 33565.00331872981, "count": 3437367, "self": 352.38222152832896, "children": { "process_trajectory": { "total": 5930.971878269687, "count": 3437367, "self": 5923.677744247019, "children": { "RLTrainer._checkpoint": { "total": 7.294134022668004, "count": 100, "self": 7.294134022668004 } } }, "_update_policy": { "total": 27281.649218931794, "count": 2424, "self": 4282.0166029874235, "children": { "TorchPOCAOptimizer.update": { "total": 22999.63261594437, "count": 72720, "self": 22999.63261594437 } } } } } } }, "trainer_threads": { "total": 6.910413503646851e-07, "count": 1, "self": 6.910413503646851e-07 }, "TrainerController._save_models": { "total": 0.0709439180791378, "count": 1, "self": 0.0010833581909537315, "children": { "RLTrainer._checkpoint": { "total": 0.06986055988818407, "count": 1, "self": 0.06986055988818407 } } } } } } }