{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4306063652038574, "min": 1.3268777132034302, "max": 1.4792799949645996, "count": 1140 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30260.185546875, "min": 16392.0703125, "max": 34403.41796875, "count": 1140 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 83.28571428571429, "min": 43.705357142857146, "max": 124.88372093023256, "count": 1140 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20988.0, "min": 10196.0, "max": 21480.0, "count": 1140 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1773.6463118042361, "min": 1714.5049530258334, "max": 1831.3569180148488, "count": 1140 }, "SoccerTwos.Self-play.ELO.sum": { "value": 223479.43528733376, "min": 146769.60746478586, "max": 398132.5771840739, "count": 1140 }, "SoccerTwos.Step.mean": { "value": 59999856.0, "min": 48609899.0, "max": 59999856.0, "count": 1140 }, "SoccerTwos.Step.sum": { "value": 59999856.0, "min": 48609899.0, "max": 59999856.0, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011984286829829216, "min": -0.12386853247880936, "max": 0.07673578709363937, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.4980359077453613, "min": -26.879470825195312, "max": 10.666274070739746, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01197702344506979, "min": -0.12527109682559967, "max": 0.07612409442663193, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.497127890586853, "min": -27.183828353881836, "max": 10.581249237060547, "count": 1140 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1140 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.16760000133514405, "min": -0.45308872093831687, "max": 0.35357837821986227, "count": 1140 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.950000166893005, "min": -60.26079988479614, "max": 52.32959997653961, "count": 1140 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.16760000133514405, "min": -0.45308872093831687, "max": 0.35357837821986227, "count": 1140 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.950000166893005, "min": -60.26079988479614, "max": 52.32959997653961, "count": 1140 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1140 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1140 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015749097906518728, "min": 0.012291531917677881, "max": 0.027052302604230742, "count": 552 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015749097906518728, "min": 0.012291531917677881, "max": 0.027052302604230742, "count": 552 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08313023646672567, "min": 0.06675376556813717, "max": 0.12261631985505422, "count": 552 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08313023646672567, "min": 0.06675376556813717, "max": 0.12261631985505422, "count": 552 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08402771850426992, "min": 0.06726417231063048, "max": 0.12480675975481668, "count": 552 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08402771850426992, "min": 0.06726417231063048, "max": 0.12480675975481668, "count": 552 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 552 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 552 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 552 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 552 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 552 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 552 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676387181", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:28:38) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\wspzo\\mambaforge\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676512851" }, "total": 125669.42330159999, "count": 1, "self": 4.9528797999810195, "children": { "run_training.setup": { "total": 0.33696190000000037, "count": 1, "self": 0.33696190000000037 }, "TrainerController.start_learning": { "total": 125664.13345990001, "count": 1, "self": 37.580279507426894, "children": { "TrainerController._reset_env": { "total": 15.784248199986397, "count": 58, "self": 15.784248199986397 }, "TrainerController.advance": { "total": 125610.41518069261, "count": 778993, "self": 41.16833799694723, "children": { "env_step": { "total": 30563.226009794795, "count": 778993, "self": 24488.141989801217, "children": { "SubprocessEnvManager._take_step": { "total": 6051.034633493797, "count": 778993, "self": 234.8993511885692, "children": { "TorchPolicy.evaluate": { "total": 5816.1352823052275, "count": 1430588, "self": 5816.1352823052275 } } }, "workers": { "total": 24.049386499780738, "count": 778993, "self": 0.0, "children": { "worker_root": { "total": 125589.69329669444, "count": 778993, "is_parallel": true, "self": 105712.13803419514, "children": { "steps_from_proto": { "total": 0.21943199993723717, "count": 116, "is_parallel": true, "self": 0.04439199990473952, "children": { "_process_rank_one_or_two_observation": { "total": 0.17504000003249764, "count": 464, "is_parallel": true, "self": 0.17504000003249764 } } }, "UnityEnvironment.step": { "total": 19877.335830499356, "count": 778993, "is_parallel": true, "self": 1043.1592854950832, "children": { "UnityEnvironment._generate_step_input": { "total": 904.3429011973393, "count": 778993, "is_parallel": true, "self": 904.3429011973393 }, "communicator.exchange": { "total": 14439.146355393024, "count": 778993, "is_parallel": true, "self": 14439.146355393024 }, "steps_from_proto": { "total": 3490.68728841391, "count": 1557986, "is_parallel": true, "self": 721.2705505021886, "children": { "_process_rank_one_or_two_observation": { "total": 2769.4167379117216, "count": 6231944, "is_parallel": true, "self": 2769.4167379117216 } } } } } } } } } } }, "trainer_advance": { "total": 95006.02083290086, "count": 778993, "self": 237.79583100328455, "children": { "process_trajectory": { "total": 7402.850478997344, "count": 778993, "self": 7393.232639397315, "children": { "RLTrainer._checkpoint": { "total": 9.617839600028674, "count": 23, "self": 9.617839600028674 } } }, "_update_policy": { "total": 87365.37452290024, "count": 552, "self": 3695.368661800385, "children": { "TorchPOCAOptimizer.update": { "total": 83670.00586109985, "count": 16560, "self": 83670.00586109985 } } } } } } }, "trainer_threads": { "total": 1.2999953469261527e-06, "count": 1, "self": 1.2999953469261527e-06 }, "TrainerController._save_models": { "total": 0.3537501999962842, "count": 1, "self": 0.06820199999492615, "children": { "RLTrainer._checkpoint": { "total": 0.28554820000135805, "count": 1, "self": 0.28554820000135805 } } } } } } }