{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.041991710662842, "min": 1.9938650131225586, "max": 3.2957613468170166, "count": 415 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38356.7734375, "min": 16520.703125, "max": 139459.5, "count": 415 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.84705882352941, "min": 40.90833333333333, "max": 999.0, "count": 415 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19668.0, "min": 14744.0, "max": 25592.0, "count": 415 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1530.6660057602103, "min": 1197.5937757826562, "max": 1538.2346070756448, "count": 398 }, "SoccerTwos.Self-play.ELO.sum": { "value": 260213.22097923575, "min": 2398.030062920268, "max": 353862.93577930244, "count": 398 }, "SoccerTwos.Step.mean": { "value": 4149999.0, "min": 9814.0, "max": 4149999.0, "count": 415 }, "SoccerTwos.Step.sum": { "value": 4149999.0, "min": 9814.0, "max": 4149999.0, "count": 415 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0636613741517067, "min": -0.08738914132118225, "max": 0.15419864654541016, "count": 415 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.822433471679688, "min": -17.652606964111328, "max": 22.087421417236328, "count": 415 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.060710322111845016, "min": -0.08959988504648209, "max": 0.15101510286331177, "count": 415 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.320755004882812, "min": -18.09917640686035, "max": 20.66999626159668, "count": 415 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 415 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 415 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14556235250304728, "min": -0.6202086935872617, "max": 0.5334727201949466, "count": 415 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -24.745599925518036, "min": -37.232800126075745, "max": 58.78880017995834, "count": 415 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14556235250304728, "min": -0.6202086935872617, "max": 0.5334727201949466, "count": 415 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -24.745599925518036, "min": -37.232800126075745, "max": 58.78880017995834, "count": 415 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 415 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 415 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0156176461285213, "min": 0.011218969126154358, "max": 0.02241866645247986, "count": 198 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0156176461285213, "min": 0.011218969126154358, "max": 0.02241866645247986, "count": 198 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10335909724235534, "min": 1.7910415711715663e-06, "max": 0.11775548780957858, "count": 198 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10335909724235534, "min": 1.7910415711715663e-06, "max": 0.11775548780957858, "count": 198 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10451662813623747, "min": 2.237098567547946e-06, "max": 0.12151149138808251, "count": 198 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10451662813623747, "min": 2.237098567547946e-06, "max": 0.12151149138808251, "count": 198 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 198 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 198 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 198 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 198 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 198 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 198 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703616628", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/andrea/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --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+cu121", "numpy_version": "1.22.4", "end_time_seconds": "1703624758" }, "total": 8129.363811496001, "count": 1, "self": 0.00775329300086014, "children": { "run_training.setup": { "total": 0.027763978999701067, "count": 1, "self": 0.027763978999701067 }, "TrainerController.start_learning": { "total": 8129.328294224, "count": 1, "self": 4.880468948102134, "children": { "TrainerController._reset_env": { "total": 3.7062295859955157, "count": 21, "self": 3.7062295859955157 }, "TrainerController.advance": { "total": 8120.357086630902, "count": 282322, "self": 5.5937927678533015, "children": { "env_step": { "total": 6483.21319187393, "count": 282322, "self": 5373.501489496242, "children": { "SubprocessEnvManager._take_step": { "total": 1106.0433786474982, "count": 282322, "self": 40.240045743285464, "children": { "TorchPolicy.evaluate": { "total": 1065.8033329042128, "count": 526364, "self": 1065.8033329042128 } } }, "workers": { "total": 3.668323730188604, "count": 282322, "self": 0.0, "children": { "worker_root": { "total": 8115.8699042782255, "count": 282322, "is_parallel": true, "self": 3390.109099815555, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.032612723000056576, "count": 2, "is_parallel": true, "self": 0.030268004000390647, "children": { "_process_rank_one_or_two_observation": { "total": 0.002344718999665929, "count": 8, "is_parallel": true, "self": 0.002344718999665929 } } }, "UnityEnvironment.step": { "total": 0.030425074999584467, "count": 1, "is_parallel": true, "self": 0.00195026700021117, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0014961709998715378, "count": 1, "is_parallel": true, "self": 0.0014961709998715378 }, "communicator.exchange": { "total": 0.025414511999770184, "count": 1, "is_parallel": true, "self": 0.025414511999770184 }, "steps_from_proto": { "total": 0.0015641249997315754, "count": 2, "is_parallel": true, "self": 0.0002617589993860747, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013023660003455007, "count": 8, "is_parallel": true, "self": 0.0013023660003455007 } } } } } } }, "UnityEnvironment.step": { "total": 4725.684832301666, "count": 282321, "is_parallel": true, "self": 285.9514042650717, "children": { "UnityEnvironment._generate_step_input": { "total": 182.3319607654821, "count": 282321, "is_parallel": true, "self": 182.3319607654821 }, "communicator.exchange": { "total": 3444.762629923959, "count": 282321, "is_parallel": true, "self": 3444.762629923959 }, "steps_from_proto": { "total": 812.6388373471527, "count": 564642, "is_parallel": true, "self": 125.45612937184114, "children": { "_process_rank_one_or_two_observation": { "total": 687.1827079753116, "count": 2258568, "is_parallel": true, "self": 687.1827079753116 } } } } }, "steps_from_proto": { "total": 0.07597216100521109, "count": 40, "is_parallel": true, "self": 0.011521899003582803, "children": { "_process_rank_one_or_two_observation": { "total": 0.06445026200162829, "count": 160, "is_parallel": true, "self": 0.06445026200162829 } } } } } } } } }, "trainer_advance": { "total": 1631.5501019891194, "count": 282322, "self": 40.807156736239904, "children": { "process_trajectory": { "total": 529.0671589648682, "count": 282322, "self": 526.2703316878687, "children": { "RLTrainer._checkpoint": { "total": 2.7968272769994655, "count": 8, "self": 2.7968272769994655 } } }, "_update_policy": { "total": 1061.6757862880113, "count": 199, "self": 524.5038099489575, "children": { "TorchPOCAOptimizer.update": { "total": 537.1719763390538, "count": 5956, "self": 537.1719763390538 } } } } } } }, "trainer_threads": { "total": 1.8850005290005356e-06, "count": 1, "self": 1.8850005290005356e-06 }, "TrainerController._save_models": { "total": 0.38450717399973655, "count": 1, "self": 0.002288846999363159, "children": { "RLTrainer._checkpoint": { "total": 0.3822183270003734, "count": 1, "self": 0.3822183270003734 } } } } } } }