{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2608132362365723, "min": 3.2543694972991943, "max": 3.2923762798309326, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 322429.21875, "min": 312926.0, "max": 384171.8125, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 831.1, "min": 613.3, "max": 850.3448275862069, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 99732.0, "min": 98128.0, "max": 102060.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.3552278697719, "min": 1193.357593415445, "max": 1197.7831063360754, "count": 10 }, "SoccerTwos.Self-play.ELO.sum": { "value": 21498.394101655893, "min": 14340.227908178333, "max": 50121.01892344869, "count": 10 }, "SoccerTwos.Step.mean": { "value": 499550.0, "min": 49092.0, "max": 499550.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 499550.0, "min": 49092.0, "max": 499550.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012013890780508518, "min": -0.0667295753955841, "max": -0.01047731377184391, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.720833420753479, "min": -4.003774642944336, "max": -0.6705480813980103, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012075837701559067, "min": -0.06578823179006577, "max": -0.010246561840176582, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7245502471923828, "min": -3.947293758392334, "max": -0.6557799577713013, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.15586666564146678, "min": -0.21238666598995526, "max": 0.03416811620843583, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.351999938488007, "min": -12.743199959397316, "max": 2.3576000183820724, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.15586666564146678, "min": -0.21238666598995526, "max": 0.03416811620843583, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.351999938488007, "min": -12.743199959397316, "max": 2.3576000183820724, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019329489871355084, "min": 0.014744656465457714, "max": 0.019329489871355084, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03865897974271017, "min": 0.029489312930915428, "max": 0.0524223680239326, "count": 10 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0019155810189355786, "min": 0.0018330100419310233, "max": 0.004667250857649682, "count": 10 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003831162037871157, "min": 0.0036660200838620465, "max": 0.009334501715299363, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0019199513568310068, "min": 0.0018394033637984346, "max": 0.004676262878638227, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0038399027136620137, "min": 0.003678806727596869, "max": 0.009352525757276454, "count": 10 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 10 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006, "min": 0.0006, "max": 0.0009, "count": 10 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 10 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.40000000000000013, "min": 0.4000000000000001, "max": 0.6000000000000002, "count": 10 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 10 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.015000000000000003, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678732566", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1678738453" }, "total": 888.716972542, "count": 1, "self": 0.7680651670000316, "children": { "run_training.setup": { "total": 0.030166166999999966, "count": 1, "self": 0.030166166999999966 }, "TrainerController.start_learning": { "total": 887.918741208, "count": 1, "self": 0.5241852780006866, "children": { "TrainerController._reset_env": { "total": 3.256744875000112, "count": 5, "self": 3.256744875000112 }, "TrainerController.advance": { "total": 884.0348267629993, "count": 33641, "self": 0.48526317500261484, "children": { "env_step": { "total": 552.3586291570094, "count": 33641, "self": 476.7615190060085, "children": { "SubprocessEnvManager._take_step": { "total": 75.23774770800605, "count": 33641, "self": 2.713648641018125, "children": { "TorchPolicy.evaluate": { "total": 72.52409906698793, "count": 66768, "self": 72.52409906698793 } } }, "workers": { "total": 0.3593624429948754, "count": 33641, "self": 0.0, "children": { "worker_root": { "total": 883.5617169189921, "count": 33641, "is_parallel": true, "self": 473.0885230489916, "children": { "steps_from_proto": { "total": 0.01051604200013978, "count": 10, "is_parallel": true, "self": 0.002012794000232354, "children": { "_process_rank_one_or_two_observation": { "total": 0.008503247999907426, "count": 40, "is_parallel": true, "self": 0.008503247999907426 } } }, "UnityEnvironment.step": { "total": 410.46267782800044, "count": 33641, "is_parallel": true, "self": 18.002323263983783, "children": { "UnityEnvironment._generate_step_input": { "total": 11.918808152011675, "count": 33641, "is_parallel": true, "self": 11.918808152011675 }, "communicator.exchange": { "total": 322.152185683006, "count": 33641, "is_parallel": true, "self": 322.152185683006 }, "steps_from_proto": { "total": 58.38936072899899, "count": 67282, "is_parallel": true, "self": 9.220504493991811, "children": { "_process_rank_one_or_two_observation": { "total": 49.168856235007176, "count": 269128, "is_parallel": true, "self": 49.168856235007176 } } } } } } } } } } }, "trainer_advance": { "total": 331.1909344309872, "count": 33641, "self": 3.894702732973485, "children": { "process_trajectory": { "total": 52.48889886401393, "count": 33641, "self": 52.32414244701401, "children": { "RLTrainer._checkpoint": { "total": 0.16475641699992138, "count": 1, "self": 0.16475641699992138 } } }, "_update_policy": { "total": 274.8073328339998, "count": 23, "self": 74.17287908299795, "children": { "TorchPOCAOptimizer.update": { "total": 200.63445375100184, "count": 693, "self": 200.63445375100184 } } } } } } }, "trainer_threads": { "total": 6.24999984211172e-07, "count": 1, "self": 6.24999984211172e-07 }, "TrainerController._save_models": { "total": 0.10298366699998951, "count": 1, "self": 0.0009620829999903435, "children": { "RLTrainer._checkpoint": { "total": 0.10202158399999917, "count": 1, "self": 0.10202158399999917 } } } } } } }