{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.708724856376648, "min": 1.7064248323440552, "max": 3.2957451343536377, "count": 732 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32971.5546875, "min": 24871.140625, "max": 117462.03125, "count": 732 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.86046511627907, "min": 42.623931623931625, "max": 999.0, "count": 732 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19560.0, "min": 15684.0, "max": 24116.0, "count": 732 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1685.0793199363181, "min": 1193.4910462215628, "max": 1695.0795841448596, "count": 724 }, "SoccerTwos.Self-play.ELO.sum": { "value": 289833.6430290467, "min": 2388.434782969469, "max": 359412.9854283597, "count": 724 }, "SoccerTwos.Step.mean": { "value": 7319971.0, "min": 9388.0, "max": 7319971.0, "count": 732 }, "SoccerTwos.Step.sum": { "value": 7319971.0, "min": 9388.0, "max": 7319971.0, "count": 732 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0049272398464381695, "min": -0.11839887499809265, "max": 0.28475695848464966, "count": 732 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.8474852442741394, "min": -18.907867431640625, "max": 33.38478088378906, "count": 732 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0020954858046025038, "min": -0.12036605179309845, "max": 0.2840828597545624, "count": 732 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.36042356491088867, "min": -18.86254119873047, "max": 35.508243560791016, "count": 732 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 732 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 732 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0034000003753706467, "min": -0.5798500031232834, "max": 0.7870892286300659, "count": 732 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.5848000645637512, "min": -61.92040002346039, "max": 82.3407998085022, "count": 732 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0034000003753706467, "min": -0.5798500031232834, "max": 0.7870892286300659, "count": 732 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.5848000645637512, "min": -61.92040002346039, "max": 82.3407998085022, "count": 732 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 732 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 732 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018750305784245334, "min": 0.009751158613168324, "max": 0.02430557073870053, "count": 352 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018750305784245334, "min": 0.009751158613168324, "max": 0.02430557073870053, "count": 352 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0903317871193091, "min": 0.00022427343671248915, "max": 0.12271761645873387, "count": 352 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0903317871193091, "min": 0.00022427343671248915, "max": 0.12271761645873387, "count": 352 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09221188401182492, "min": 0.00023013590713768888, "max": 0.125553181519111, "count": 352 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09221188401182492, "min": 0.00023013590713768888, "max": 0.125553181519111, "count": 352 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 352 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 352 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 352 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 352 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 352 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 352 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697628129", "python_version": "3.9.18 (main, Oct 12 2023, 10:28:59) \n[GCC 12.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1697670855" }, "total": 42726.52308258999, "count": 1, "self": 5.807829872996081, "children": { "run_training.setup": { "total": 0.049611725999056944, "count": 1, "self": 0.049611725999056944 }, "TrainerController.start_learning": { "total": 42720.665640991, "count": 1, "self": 13.592370800433855, "children": { "TrainerController._reset_env": { "total": 2.942965879015901, "count": 37, "self": 2.942965879015901 }, "TrainerController.advance": { "total": 42703.64870191455, "count": 497538, "self": 15.770513132614724, "children": { "env_step": { "total": 11328.624999491014, "count": 497538, "self": 9004.069677347408, "children": { "SubprocessEnvManager._take_step": { "total": 2315.999565461385, "count": 497538, "self": 96.48767579956439, "children": { "TorchPolicy.evaluate": { "total": 2219.5118896618205, "count": 923806, "self": 2219.5118896618205 } } }, "workers": { "total": 8.555756682220817, "count": 497538, "self": 0.0, "children": { "worker_root": { "total": 42657.193368692744, "count": 497538, "is_parallel": true, "self": 37187.09496959218, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022913849988981383, "count": 2, "is_parallel": true, "self": 0.0005575740015046904, "children": { "_process_rank_one_or_two_observation": { "total": 0.001733810997393448, "count": 8, "is_parallel": true, "self": 0.001733810997393448 } } }, "UnityEnvironment.step": { "total": 0.5914581790002558, "count": 1, "is_parallel": true, "self": 0.0005390770002122736, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003947080003854353, "count": 1, "is_parallel": true, "self": 0.0003947080003854353 }, "communicator.exchange": { "total": 0.5887967029993888, "count": 1, "is_parallel": true, "self": 0.5887967029993888 }, "steps_from_proto": { "total": 0.0017276910002692603, "count": 2, "is_parallel": true, "self": 0.0003886720005539246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013390189997153357, "count": 8, "is_parallel": true, "self": 0.0013390189997153357 } } } } } } }, "UnityEnvironment.step": { "total": 5470.038002831581, "count": 497537, "is_parallel": true, "self": 270.53645578644864, "children": { "UnityEnvironment._generate_step_input": { "total": 194.69159653869792, "count": 497537, "is_parallel": true, "self": 194.69159653869792 }, "communicator.exchange": { "total": 4198.232304760157, "count": 497537, "is_parallel": true, "self": 4198.232304760157 }, "steps_from_proto": { "total": 806.577645746278, "count": 995074, "is_parallel": true, "self": 177.63399145457151, "children": { "_process_rank_one_or_two_observation": { "total": 628.9436542917065, "count": 3980296, "is_parallel": true, "self": 628.9436542917065 } } } } }, "steps_from_proto": { "total": 0.060396268982003676, "count": 72, "is_parallel": true, "self": 0.01267577093494765, "children": { "_process_rank_one_or_two_observation": { "total": 0.047720498047056026, "count": 288, "is_parallel": true, "self": 0.047720498047056026 } } } } } } } } }, "trainer_advance": { "total": 31359.253189290925, "count": 497538, "self": 94.78139855978588, "children": { "process_trajectory": { "total": 4191.7285584602, "count": 497538, "self": 4185.71359065821, "children": { "RLTrainer._checkpoint": { "total": 6.014967801989769, "count": 14, "self": 6.014967801989769 } } }, "_update_policy": { "total": 27072.74323227094, "count": 353, "self": 1527.76111380976, "children": { "TorchPOCAOptimizer.update": { "total": 25544.98211846118, "count": 10584, "self": 25544.98211846118 } } } } } } }, "trainer_threads": { "total": 1.1309966794215143e-06, "count": 1, "self": 1.1309966794215143e-06 }, "TrainerController._save_models": { "total": 0.48160126600123476, "count": 1, "self": 0.03382706000411417, "children": { "RLTrainer._checkpoint": { "total": 0.4477742059971206, "count": 1, "self": 0.4477742059971206 } } } } } } }