{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0314760208129883, "min": 2.001591682434082, "max": 3.188758134841919, "count": 1550 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40824.54296875, "min": 14608.048828125, "max": 106544.6953125, "count": 1550 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 89.54545454545455, "min": 52.68817204301075, "max": 811.0, "count": 1550 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19700.0, "min": 716.0, "max": 23712.0, "count": 1550 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1391.3625857831264, "min": 1216.2215412605815, "max": 1434.7892859930016, "count": 1550 }, "SoccerTwos.Self-play.ELO.sum": { "value": 153049.8844361439, "min": 4877.785150332238, "max": 262788.582880683, "count": 1550 }, "SoccerTwos.Step.mean": { "value": 17989876.0, "min": 2499972.0, "max": 17989876.0, "count": 1550 }, "SoccerTwos.Step.sum": { "value": 17989876.0, "min": 2499972.0, "max": 17989876.0, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03356821462512016, "min": -0.12719358503818512, "max": 0.150315061211586, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.6925036907196045, "min": -18.02039337158203, "max": 20.058128356933594, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.029394764453172684, "min": -0.13260090351104736, "max": 0.1479911208152771, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.233424186706543, "min": -18.494277954101562, "max": 19.611934661865234, "count": 1550 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1550 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.019403636997396296, "min": -0.6248296278494375, "max": 0.9607999920845032, "count": 1550 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.1344000697135925, "min": -61.121999859809875, "max": 53.99279999732971, "count": 1550 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.019403636997396296, "min": -0.6248296278494375, "max": 0.9607999920845032, "count": 1550 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.1344000697135925, "min": -61.121999859809875, "max": 53.99279999732971, "count": 1550 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1550 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1550 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.03322674172517509, "min": 0.011198681086480065, "max": 0.03322674172517509, "count": 37 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03322674172517509, "min": 0.011198681086480065, "max": 0.03322674172517509, "count": 37 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.04035536533687264, "min": 0.009418043367331848, "max": 0.04121233653044328, "count": 37 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.04035536533687264, "min": 0.009418043367331848, "max": 0.04121233653044328, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.060639107818715274, "min": 0.011299039868172258, "max": 0.06512493243906647, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.060639107818715274, "min": 0.011299039868172258, "max": 0.06512493243906647, "count": 37 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 37 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 37 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 37 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689619672", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Gyana\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_ultimate_poca --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1689674052" }, "total": 54380.020052700005, "count": 1, "self": 5.717671400001564, "children": { "run_training.setup": { "total": 0.1751073999999999, "count": 1, "self": 0.1751073999999999 }, "TrainerController.start_learning": { "total": 54374.127273900005, "count": 1, "self": 27.705745701990963, "children": { "TrainerController._reset_env": { "total": 9.85503369999277, "count": 79, "self": 9.85503369999277 }, "TrainerController.advance": { "total": 54335.62383159802, "count": 1046883, "self": 30.777867692413565, "children": { "env_step": { "total": 33647.08669760124, "count": 1046883, "self": 19353.322100501893, "children": { "SubprocessEnvManager._take_step": { "total": 14276.506041698649, "count": 1046883, "self": 205.0378667997902, "children": { "TorchPolicy.evaluate": { "total": 14071.468174898859, "count": 1949568, "self": 14071.468174898859 } } }, "workers": { "total": 17.25855540070058, "count": 1046882, "self": 0.0, "children": { "worker_root": { "total": 54306.66124680051, "count": 1046882, "is_parallel": true, "self": 38131.88634169927, "children": { "steps_from_proto": { "total": 0.14612619999789267, "count": 158, "is_parallel": true, "self": 0.030273900001013487, "children": { "_process_rank_one_or_two_observation": { "total": 0.11585229999687918, "count": 632, "is_parallel": true, "self": 0.11585229999687918 } } }, "UnityEnvironment.step": { "total": 16174.62877890125, "count": 1046882, "is_parallel": true, "self": 586.3628733106507, "children": { "UnityEnvironment._generate_step_input": { "total": 386.89703819618353, "count": 1046882, "is_parallel": true, "self": 386.89703819618353 }, "communicator.exchange": { "total": 13382.14408799565, "count": 1046882, "is_parallel": true, "self": 13382.14408799565 }, "steps_from_proto": { "total": 1819.2247793987644, "count": 2093764, "is_parallel": true, "self": 373.9608832027877, "children": { "_process_rank_one_or_two_observation": { "total": 1445.2638961959767, "count": 8375056, "is_parallel": true, "self": 1445.2638961959767 } } } } } } } } } } }, "trainer_advance": { "total": 20657.75926630437, "count": 1046882, "self": 255.99044580684858, "children": { "process_trajectory": { "total": 5186.045373797518, "count": 1046882, "self": 5157.814130397507, "children": { "RLTrainer._checkpoint": { "total": 28.231243400010836, "count": 31, "self": 28.231243400010836 } } }, "_update_policy": { "total": 15215.723446700002, "count": 37, "self": 8774.033798200238, "children": { "TorchPOCAOptimizer.update": { "total": 6441.689648499762, "count": 29600, "self": 6441.689648499762 } } } } } } }, "trainer_threads": { "total": 2.2000021999701858e-06, "count": 1, "self": 2.2000021999701858e-06 }, "TrainerController._save_models": { "total": 0.9426606999986689, "count": 1, "self": 0.1667144000020926, "children": { "RLTrainer._checkpoint": { "total": 0.7759462999965763, "count": 1, "self": 0.7759462999965763 } } } } } } }