{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6685035228729248, "min": 1.576264500617981, "max": 3.2957048416137695, "count": 1125 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32782.7578125, "min": 27321.90625, "max": 110772.0625, "count": 1125 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.674157303370784, "min": 39.235772357723576, "max": 999.0, "count": 1125 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19464.0, "min": 13020.0, "max": 27040.0, "count": 1125 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1626.8769388625344, "min": 1193.6688393011011, "max": 1666.2055540957253, "count": 1122 }, "SoccerTwos.Self-play.ELO.sum": { "value": 289584.09511753113, "min": 2396.1785651367168, "max": 393239.04171339865, "count": 1122 }, "SoccerTwos.Step.mean": { "value": 11249973.0, "min": 9538.0, "max": 11249973.0, "count": 1125 }, "SoccerTwos.Step.sum": { "value": 11249973.0, "min": 9538.0, "max": 11249973.0, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02289056032896042, "min": -0.12461207062005997, "max": 0.16715063154697418, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.097410202026367, "min": -24.050128936767578, "max": 27.579853057861328, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.024793121963739395, "min": -0.12570492923259735, "max": 0.1686450093984604, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.437968730926514, "min": -22.261478424072266, "max": 27.826427459716797, "count": 1125 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1125 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.19148156496399607, "min": -0.6915294116034227, "max": 0.4790105243262492, "count": 1125 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -34.2752001285553, "min": -56.238800168037415, "max": 54.51539969444275, "count": 1125 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19148156496399607, "min": -0.6915294116034227, "max": 0.4790105243262492, "count": 1125 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -34.2752001285553, "min": -56.238800168037415, "max": 54.51539969444275, "count": 1125 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1125 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1125 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016712228224302333, "min": 0.010718649214444062, "max": 0.026978419835601623, "count": 544 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016712228224302333, "min": 0.010718649214444062, "max": 0.026978419835601623, "count": 544 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09912082180380821, "min": 0.0009114766047180941, "max": 0.12794776608546574, "count": 544 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09912082180380821, "min": 0.0009114766047180941, "max": 0.12794776608546574, "count": 544 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10044970785578092, "min": 0.0009156788029940799, "max": 0.12996982062856358, "count": 544 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10044970785578092, "min": 0.0009156788029940799, "max": 0.12996982062856358, "count": 544 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 544 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 544 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 544 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 544 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 544 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 544 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677619977", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "F:\\Users\\Niels\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1677654237" }, "total": 34259.90498570001, "count": 1, "self": 0.005812200004584156, "children": { "run_training.setup": { "total": 0.06886420000000015, "count": 1, "self": 0.06886420000000015 }, "TrainerController.start_learning": { "total": 34259.8303093, "count": 1, "self": 12.870827198777988, "children": { "TrainerController._reset_env": { "total": 3.21658669999282, "count": 57, "self": 3.21658669999282 }, "TrainerController.advance": { "total": 34243.62446980123, "count": 779453, "self": 11.162809000554262, "children": { "env_step": { "total": 9686.743012900537, "count": 779453, "self": 7489.50477690216, "children": { "SubprocessEnvManager._take_step": { "total": 2188.6810138002306, "count": 779453, "self": 70.00135830212639, "children": { "TorchPolicy.evaluate": { "total": 2118.6796554981042, "count": 1414136, "self": 2118.6796554981042 } } }, "workers": { "total": 8.55722219814554, "count": 779453, "self": 0.0, "children": { "worker_root": { "total": 34229.93478920081, "count": 779453, "is_parallel": true, "self": 28230.72708430112, "children": { "steps_from_proto": { "total": 0.08877500000701932, "count": 114, "is_parallel": true, "self": 0.015110099952523104, "children": { "_process_rank_one_or_two_observation": { "total": 0.07366490005449622, "count": 456, "is_parallel": true, "self": 0.07366490005449622 } } }, "UnityEnvironment.step": { "total": 5999.118929899678, "count": 779453, "is_parallel": true, "self": 342.9582357968493, "children": { "UnityEnvironment._generate_step_input": { "total": 303.02656130022547, "count": 779453, "is_parallel": true, "self": 303.02656130022547 }, "communicator.exchange": { "total": 4242.5582872005, "count": 779453, "is_parallel": true, "self": 4242.5582872005 }, "steps_from_proto": { "total": 1110.5758456021028, "count": 1558906, "is_parallel": true, "self": 190.7607114994496, "children": { "_process_rank_one_or_two_observation": { "total": 919.8151341026532, "count": 6235624, "is_parallel": true, "self": 919.8151341026532 } } } } } } } } } } }, "trainer_advance": { "total": 24545.718647900136, "count": 779453, "self": 107.36829729984674, "children": { "process_trajectory": { "total": 6366.099705400297, "count": 779453, "self": 6363.710259900289, "children": { "RLTrainer._checkpoint": { "total": 2.3894455000081507, "count": 22, "self": 2.3894455000081507 } } }, "_update_policy": { "total": 18072.25064519999, "count": 545, "self": 1594.3519775001696, "children": { "TorchPOCAOptimizer.update": { "total": 16477.89866769982, "count": 16337, "self": 16477.89866769982 } } } } } } }, "trainer_threads": { "total": 7.999988156370819e-07, "count": 1, "self": 7.999988156370819e-07 }, "TrainerController._save_models": { "total": 0.11842479999904754, "count": 1, "self": 0.001890599996841047, "children": { "RLTrainer._checkpoint": { "total": 0.11653420000220649, "count": 1, "self": 0.11653420000220649 } } } } } } }