{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9693621397018433, "min": 1.9693621397018433, "max": 3.2958312034606934, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38567.98828125, "min": 23940.580078125, "max": 130549.8671875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 91.19298245614036, "min": 63.896103896103895, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20792.0, "min": 15936.0, "max": 25408.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1436.3633610517857, "min": 1200.7447054581453, "max": 1456.3359400568088, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 163745.42315990356, "min": 2414.8185677376273, "max": 222401.58267636702, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999916.0, "min": 9722.0, "max": 4999916.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999916.0, "min": 9722.0, "max": 4999916.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03328828513622284, "min": -0.14581826329231262, "max": 0.17683535814285278, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.7615761756896973, "min": -17.18515396118164, "max": 18.582040786743164, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.021687177941203117, "min": -0.14562536776065826, "max": 0.19014842808246613, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.450651168823242, "min": -17.672834396362305, "max": 19.479516983032227, "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": 0.0660530988094026, "min": -0.5005599995454152, "max": 0.46273077164704984, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 7.464000165462494, "min": -50.86040019989014, "max": 42.979399621486664, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0660530988094026, "min": -0.5005599995454152, "max": 0.46273077164704984, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 7.464000165462494, "min": -50.86040019989014, "max": 42.979399621486664, "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": 0.049719220967963336, "min": 0.01274991297905217, "max": 0.05383361073210836, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.049719220967963336, "min": 0.01274991297905217, "max": 0.05383361073210836, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.04460492178797722, "min": 0.0005625370285997633, "max": 0.07234545573592185, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.04460492178797722, "min": 0.0005625370285997633, "max": 0.07234545573592185, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.05085183165967464, "min": 0.0006860743058496154, "max": 0.07716061219573021, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.05085183165967464, "min": 0.0006860743058496154, "max": 0.07716061219573021, "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": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676146148", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/arne/anaconda3/envs/rl2/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../SoccerTwos/SoccerTwos.x86_64 --run-id=first run --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1676149813" }, "total": 3665.017267064002, "count": 1, "self": 0.16701423400445492, "children": { "run_training.setup": { "total": 0.006198107999807689, "count": 1, "self": 0.006198107999807689 }, "TrainerController.start_learning": { "total": 3664.844054721998, "count": 1, "self": 2.9737509766346193, "children": { "TrainerController._reset_env": { "total": 2.9451986119820504, "count": 25, "self": 2.9451986119820504 }, "TrainerController.advance": { "total": 3658.5846066943886, "count": 332558, "self": 2.940329932840541, "children": { "env_step": { "total": 2300.57553591585, "count": 332558, "self": 1756.2113050449225, "children": { "SubprocessEnvManager._take_step": { "total": 542.4074856922198, "count": 332558, "self": 19.19779383495552, "children": { "TorchPolicy.evaluate": { "total": 523.2096918572643, "count": 631250, "self": 523.2096918572643 } } }, "workers": { "total": 1.9567451787079335, "count": 332558, "self": 0.0, "children": { "worker_root": { "total": 3660.5944827921376, "count": 332558, "is_parallel": true, "self": 2238.8638966365324, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010910209966823459, "count": 2, "is_parallel": true, "self": 0.00025990900030592456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008311119963764213, "count": 8, "is_parallel": true, "self": 0.0008311119963764213 } } }, "UnityEnvironment.step": { "total": 0.011647046001598937, "count": 1, "is_parallel": true, "self": 0.0003012590059370268, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019559599968488328, "count": 1, "is_parallel": true, "self": 0.00019559599968488328 }, "communicator.exchange": { "total": 0.010364205998484977, "count": 1, "is_parallel": true, "self": 0.010364205998484977 }, "steps_from_proto": { "total": 0.0007859849974920508, "count": 2, "is_parallel": true, "self": 0.0001598839917278383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006261010057642125, "count": 8, "is_parallel": true, "self": 0.0006261010057642125 } } } } } } }, "UnityEnvironment.step": { "total": 1421.712222462611, "count": 332557, "is_parallel": true, "self": 86.5455151380047, "children": { "UnityEnvironment._generate_step_input": { "total": 44.5132334888076, "count": 332557, "is_parallel": true, "self": 44.5132334888076 }, "communicator.exchange": { "total": 1060.7840537701777, "count": 332557, "is_parallel": true, "self": 1060.7840537701777 }, "steps_from_proto": { "total": 229.86942006562094, "count": 665114, "is_parallel": true, "self": 41.2072640777842, "children": { "_process_rank_one_or_two_observation": { "total": 188.66215598783674, "count": 2660456, "is_parallel": true, "self": 188.66215598783674 } } } } }, "steps_from_proto": { "total": 0.018363692994171288, "count": 48, "is_parallel": true, "self": 0.0034599000100570265, "children": { "_process_rank_one_or_two_observation": { "total": 0.014903792984114261, "count": 192, "is_parallel": true, "self": 0.014903792984114261 } } } } } } } } }, "trainer_advance": { "total": 1355.068740845698, "count": 332558, "self": 25.436886592582596, "children": { "process_trajectory": { "total": 258.2796718231184, "count": 332558, "self": 254.9649083441218, "children": { "RLTrainer._checkpoint": { "total": 3.3147634789966105, "count": 10, "self": 3.3147634789966105 } } }, "_update_policy": { "total": 1071.352182429997, "count": 240, "self": 505.0094022534249, "children": { "TorchPOCAOptimizer.update": { "total": 566.342780176572, "count": 12000, "self": 566.342780176572 } } } } } } }, "trainer_threads": { "total": 6.33997842669487e-07, "count": 1, "self": 6.33997842669487e-07 }, "TrainerController._save_models": { "total": 0.3404978049948113, "count": 1, "self": 0.0046981169944047, "children": { "RLTrainer._checkpoint": { "total": 0.3357996880004066, "count": 1, "self": 0.3357996880004066 } } } } } } }