{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8498406410217285, "min": 1.847397804260254, "max": 3.2957520484924316, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40370.921875, "min": 22338.81640625, "max": 115218.171875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.15384615384615, "min": 39.9344262295082, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20032.0, "min": 12712.0, "max": 28172.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1569.3760824336978, "min": 1198.9287916317044, "max": 1575.3067719073695, "count": 491 }, "SoccerTwos.Self-play.ELO.sum": { "value": 326430.2251462091, "min": 2403.352124755773, "max": 379166.89638808754, "count": 491 }, "SoccerTwos.Step.mean": { "value": 4999928.0, "min": 9104.0, "max": 4999928.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999928.0, "min": 9104.0, "max": 4999928.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00030533509561792016, "min": -0.1340479701757431, "max": 0.16007526218891144, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.06350970268249512, "min": -30.16079330444336, "max": 27.242170333862305, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0011261050822213292, "min": -0.12452097237110138, "max": 0.16851264238357544, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.23422986268997192, "min": -28.01721954345703, "max": 26.100231170654297, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.156488462136342, "min": -0.46153846153846156, "max": 0.46030666629473366, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -32.54960012435913, "min": -64.9243997335434, "max": 56.925599694252014, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.156488462136342, "min": -0.46153846153846156, "max": 0.46030666629473366, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -32.54960012435913, "min": -64.9243997335434, "max": 56.925599694252014, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015213420743384632, "min": 0.009890492176054977, "max": 0.025273329729679973, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015213420743384632, "min": 0.009890492176054977, "max": 0.025273329729679973, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11249540771047274, "min": 7.357478219394882e-05, "max": 0.12609227895736694, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11249540771047274, "min": 7.357478219394882e-05, "max": 0.12609227895736694, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11473422423005104, "min": 6.646392794209532e-05, "max": 0.12873559867342313, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11473422423005104, "min": 6.646392794209532e-05, "max": 0.12873559867342313, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705545396", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\hazem\\anaconda3\\envs\\rl2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1705562907" }, "total": 17510.391402700014, "count": 1, "self": 12.079760100023123, "children": { "run_training.setup": { "total": 0.10511549998773262, "count": 1, "self": 0.10511549998773262 }, "TrainerController.start_learning": { "total": 17498.206527100003, "count": 1, "self": 9.904199307580711, "children": { "TrainerController._reset_env": { "total": 23.894243299931986, "count": 25, "self": 23.894243299931986 }, "TrainerController.advance": { "total": 17460.972794092464, "count": 342556, "self": 10.442792986985296, "children": { "env_step": { "total": 7150.955410609895, "count": 342556, "self": 5524.283039325499, "children": { "SubprocessEnvManager._take_step": { "total": 1620.3945509917103, "count": 342556, "self": 60.49473507993389, "children": { "TorchPolicy.evaluate": { "total": 1559.8998159117764, "count": 631144, "self": 1559.8998159117764 } } }, "workers": { "total": 6.277820292685647, "count": 342556, "self": 0.0, "children": { "worker_root": { "total": 17456.62176100674, "count": 342556, "is_parallel": true, "self": 13099.354612994939, "children": { "steps_from_proto": { "total": 0.050975099962670356, "count": 50, "is_parallel": true, "self": 0.010099100094521418, "children": { "_process_rank_one_or_two_observation": { "total": 0.04087599986814894, "count": 200, "is_parallel": true, "self": 0.04087599986814894 } } }, "UnityEnvironment.step": { "total": 4357.216172911838, "count": 342556, "is_parallel": true, "self": 217.58818619675003, "children": { "UnityEnvironment._generate_step_input": { "total": 208.6388254086196, "count": 342556, "is_parallel": true, "self": 208.6388254086196 }, "communicator.exchange": { "total": 3198.897393096471, "count": 342556, "is_parallel": true, "self": 3198.897393096471 }, "steps_from_proto": { "total": 732.0917682099971, "count": 685112, "is_parallel": true, "self": 149.0753828828747, "children": { "_process_rank_one_or_two_observation": { "total": 583.0163853271224, "count": 2740448, "is_parallel": true, "self": 583.0163853271224 } } } } } } } } } } }, "trainer_advance": { "total": 10299.574590495584, "count": 342556, "self": 75.59635449948837, "children": { "process_trajectory": { "total": 1843.6895423959068, "count": 342556, "self": 1833.567360295914, "children": { "RLTrainer._checkpoint": { "total": 10.122182099992642, "count": 10, "self": 10.122182099992642 } } }, "_update_policy": { "total": 8380.288693600189, "count": 240, "self": 827.925356701744, "children": { "TorchPOCAOptimizer.update": { "total": 7552.363336898445, "count": 7200, "self": 7552.363336898445 } } } } } } }, "trainer_threads": { "total": 2.900022082030773e-06, "count": 1, "self": 2.900022082030773e-06 }, "TrainerController._save_models": { "total": 3.4352875000040513, "count": 1, "self": 2.068576199992094, "children": { "RLTrainer._checkpoint": { "total": 1.366711300011957, "count": 1, "self": 1.366711300011957 } } } } } } }