{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9973961114883423, "min": 1.9672212600708008, "max": 3.295731544494629, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41737.58984375, "min": 20642.34375, "max": 168492.96875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.25, "min": 39.56910569105691, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19680.0, "min": 16220.0, "max": 23488.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1428.967954442669, "min": 1191.9478556453585, "max": 1446.3898811364495, "count": 459 }, "SoccerTwos.Self-play.ELO.sum": { "value": 274361.84725299245, "min": 2384.257118072176, "max": 344398.37367817503, "count": 459 }, "SoccerTwos.Step.mean": { "value": 4999972.0, "min": 9762.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999972.0, "min": 9762.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.023390689864754677, "min": -0.11991755664348602, "max": 0.13205336034297943, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.4910125732421875, "min": -26.9814510345459, "max": 26.146564483642578, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02350303716957569, "min": -0.12512031197547913, "max": 0.13728852570056915, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.512583255767822, "min": -28.152069091796875, "max": 27.183128356933594, "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": -0.07863125080863635, "min": -0.7142857142857143, "max": 0.38127500005066395, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.097200155258179, "min": -72.37800002098083, "max": 41.1385999917984, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07863125080863635, "min": -0.7142857142857143, "max": 0.38127500005066395, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.097200155258179, "min": -72.37800002098083, "max": 41.1385999917984, "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": 0.015707269603929794, "min": 0.010822808059553305, "max": 0.024873007297477063, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015707269603929794, "min": 0.010822808059553305, "max": 0.024873007297477063, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0981605698664983, "min": 6.071955779892354e-06, "max": 0.12207058742642403, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0981605698664983, "min": 6.071955779892354e-06, "max": 0.12207058742642403, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09878558243314425, "min": 5.733635695529907e-06, "max": 0.12399258886774381, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09878558243314425, "min": 5.733635695529907e-06, "max": 0.12399258886774381, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729574893", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/byeung/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1729590393" }, "total": 15499.309189803898, "count": 1, "self": 10.00968683604151, "children": { "run_training.setup": { "total": 0.024166137911379337, "count": 1, "self": 0.024166137911379337 }, "TrainerController.start_learning": { "total": 15489.275336829945, "count": 1, "self": 5.296790755353868, "children": { "TrainerController._reset_env": { "total": 4.974303150549531, "count": 50, "self": 4.974303150549531 }, "TrainerController.advance": { "total": 15478.814608255401, "count": 343372, "self": 5.434555969201028, "children": { "env_step": { "total": 10587.658404042013, "count": 343372, "self": 9214.894986375235, "children": { "SubprocessEnvManager._take_step": { "total": 1369.6727111088112, "count": 343372, "self": 44.204565349034965, "children": { "TorchPolicy.evaluate": { "total": 1325.4681457597762, "count": 646164, "self": 1325.4681457597762 } } }, "workers": { "total": 3.0907065579667687, "count": 343372, "self": 0.0, "children": { "worker_root": { "total": 15471.547301323153, "count": 343372, "is_parallel": true, "self": 7206.153205802664, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005706407129764557, "count": 2, "is_parallel": true, "self": 0.001284855417907238, "children": { "_process_rank_one_or_two_observation": { "total": 0.004421551711857319, "count": 8, "is_parallel": true, "self": 0.004421551711857319 } } }, "UnityEnvironment.step": { "total": 0.04190370161086321, "count": 1, "is_parallel": true, "self": 0.0006120866164565086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010803602635860443, "count": 1, "is_parallel": true, "self": 0.0010803602635860443 }, "communicator.exchange": { "total": 0.03848050720989704, "count": 1, "is_parallel": true, "self": 0.03848050720989704 }, "steps_from_proto": { "total": 0.0017307475209236145, "count": 2, "is_parallel": true, "self": 0.0003641154617071152, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013666320592164993, "count": 8, "is_parallel": true, "self": 0.0013666320592164993 } } } } } } }, "UnityEnvironment.step": { "total": 8265.178941797465, "count": 343371, "is_parallel": true, "self": 466.2095416150987, "children": { "UnityEnvironment._generate_step_input": { "total": 329.6114039067179, "count": 343371, "is_parallel": true, "self": 329.6114039067179 }, "communicator.exchange": { "total": 6067.122285557911, "count": 343371, "is_parallel": true, "self": 6067.122285557911 }, "steps_from_proto": { "total": 1402.2357107177377, "count": 686742, "is_parallel": true, "self": 247.52160685602576, "children": { "_process_rank_one_or_two_observation": { "total": 1154.714103861712, "count": 2746968, "is_parallel": true, "self": 1154.714103861712 } } } } }, "steps_from_proto": { "total": 0.21515372302383184, "count": 98, "is_parallel": true, "self": 0.03675766568630934, "children": { "_process_rank_one_or_two_observation": { "total": 0.1783960573375225, "count": 392, "is_parallel": true, "self": 0.1783960573375225 } } } } } } } } }, "trainer_advance": { "total": 4885.721648244187, "count": 343372, "self": 57.28664831724018, "children": { "process_trajectory": { "total": 991.135653346777, "count": 343372, "self": 988.8921352447942, "children": { "RLTrainer._checkpoint": { "total": 2.2435181019827724, "count": 10, "self": 2.2435181019827724 } } }, "_update_policy": { "total": 3837.29934658017, "count": 238, "self": 596.9566940963268, "children": { "TorchPOCAOptimizer.update": { "total": 3240.3426524838433, "count": 7140, "self": 3240.3426524838433 } } } } } } }, "trainer_threads": { "total": 7.245689630508423e-07, "count": 1, "self": 7.245689630508423e-07 }, "TrainerController._save_models": { "total": 0.18963394407182932, "count": 1, "self": 0.004723397083580494, "children": { "RLTrainer._checkpoint": { "total": 0.18491054698824883, "count": 1, "self": 0.18491054698824883 } } } } } } }