{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6055675745010376, "min": 1.4875247478485107, "max": 3.295811176300049, "count": 2420 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33652.6953125, "min": 527.3297119140625, "max": 157908.453125, "count": 2420 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.5945945945946, "min": 37.9765625, "max": 999.0, "count": 2420 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19712.0, "min": 9044.0, "max": 31900.0, "count": 2420 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1686.1153239654511, "min": 1197.2849400558503, "max": 1750.715515078577, "count": 2319 }, "SoccerTwos.Self-play.ELO.sum": { "value": 249545.06794688676, "min": 2394.5698801117005, "max": 426092.6676963066, "count": 2319 }, "SoccerTwos.Step.mean": { "value": 24199796.0, "min": 9734.0, "max": 24199796.0, "count": 2420 }, "SoccerTwos.Step.sum": { "value": 24199796.0, "min": 9734.0, "max": 24199796.0, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006833486258983612, "min": -0.1149551272392273, "max": 0.1482248604297638, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.0181894302368164, "min": -25.096607208251953, "max": 27.56982421875, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.004428248852491379, "min": -0.11781862378120422, "max": 0.15132680535316467, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6598090529441833, "min": -25.269559860229492, "max": 28.146785736083984, "count": 2420 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2420 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0290657701908342, "min": -0.5714285714285714, "max": 0.3898588173529681, "count": 2420 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.330799758434296, "min": -72.610799908638, "max": 67.44040048122406, "count": 2420 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0290657701908342, "min": -0.5714285714285714, "max": 0.3898588173529681, "count": 2420 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.330799758434296, "min": -72.610799908638, "max": 67.44040048122406, "count": 2420 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2420 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2420 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020498156530447887, "min": 0.008383814156210671, "max": 0.024075864837504922, "count": 1085 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020498156530447887, "min": 0.008383814156210671, "max": 0.024075864837504922, "count": 1085 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1081407718360424, "min": 2.2772933334636035e-07, "max": 0.13698544303576152, "count": 1085 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1081407718360424, "min": 2.2772933334636035e-07, "max": 0.13698544303576152, "count": 1085 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10900740101933479, "min": 3.7239703374325475e-07, "max": 0.13833070372541745, "count": 1085 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10900740101933479, "min": 3.7239703374325475e-07, "max": 0.13833070372541745, "count": 1085 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00015, "min": 0.00015, "max": 0.00015, "count": 1085 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00015, "min": 0.00015, "max": 0.00015, "count": 1085 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 1085 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 1085 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1085 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1085 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691679997", "python_version": "3.9.3 (tags/v3.9.3:e723086, Apr 2 2021, 11:35:20) [MSC v.1928 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\sepp4\\Desktop\\ml-agents\\env\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1691741226" }, "total": 61228.198051199994, "count": 1, "self": 0.2288713999951142, "children": { "run_training.setup": { "total": 0.0902630999999996, "count": 1, "self": 0.0902630999999996 }, "TrainerController.start_learning": { "total": 61227.8789167, "count": 1, "self": 35.02719569855253, "children": { "TrainerController._reset_env": { "total": 5.856344300003699, "count": 121, "self": 5.856344300003699 }, "TrainerController.advance": { "total": 61186.821604001445, "count": 1664618, "self": 33.55510029870493, "children": { "env_step": { "total": 27146.106987004634, "count": 1664618, "self": 21252.036833308906, "children": { "SubprocessEnvManager._take_step": { "total": 5872.404264497631, "count": 1664618, "self": 186.36553130181892, "children": { "TorchPolicy.evaluate": { "total": 5686.038733195812, "count": 3055234, "self": 5686.038733195812 } } }, "workers": { "total": 21.665889198097418, "count": 1664618, "self": 0.0, "children": { "worker_root": { "total": 61173.88716729948, "count": 1664618, "is_parallel": true, "self": 43696.29633110274, "children": { "steps_from_proto": { "total": 0.18818690005060423, "count": 242, "is_parallel": true, "self": 0.03884530000332953, "children": { "_process_rank_one_or_two_observation": { "total": 0.1493416000472747, "count": 968, "is_parallel": true, "self": 0.1493416000472747 } } }, "UnityEnvironment.step": { "total": 17477.402649296688, "count": 1664618, "is_parallel": true, "self": 802.4415389917267, "children": { "UnityEnvironment._generate_step_input": { "total": 665.0511958990663, "count": 1664618, "is_parallel": true, "self": 665.0511958990663 }, "communicator.exchange": { "total": 13378.97207830305, "count": 1664618, "is_parallel": true, "self": 13378.97207830305 }, "steps_from_proto": { "total": 2630.9378361028457, "count": 3329236, "is_parallel": true, "self": 557.7289859072744, "children": { "_process_rank_one_or_two_observation": { "total": 2073.2088501955714, "count": 13316944, "is_parallel": true, "self": 2073.2088501955714 } } } } } } } } } } }, "trainer_advance": { "total": 34007.159516698106, "count": 1664617, "self": 256.4837779951704, "children": { "process_trajectory": { "total": 5860.056134002857, "count": 1664617, "self": 5853.174722902845, "children": { "RLTrainer._checkpoint": { "total": 6.881411100012201, "count": 48, "self": 6.881411100012201 } } }, "_update_policy": { "total": 27890.61960470008, "count": 1085, "self": 3063.543814500452, "children": { "TorchPOCAOptimizer.update": { "total": 24827.07579019963, "count": 32559, "self": 24827.07579019963 } } } } } } }, "trainer_threads": { "total": 1.2000018614344299e-06, "count": 1, "self": 1.2000018614344299e-06 }, "TrainerController._save_models": { "total": 0.1737714999981108, "count": 1, "self": 0.007878600001276936, "children": { "RLTrainer._checkpoint": { "total": 0.16589289999683388, "count": 1, "self": 0.16589289999683388 } } } } } } }