{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9021496772766113, "min": 1.8278286457061768, "max": 2.0336482524871826, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39808.1875, "min": 31856.9765625, "max": 49968.15234375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.15909090909091, "min": 44.46363636363636, "max": 103.45833333333333, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19768.0, "min": 18588.0, "max": 20676.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1555.385077202667, "min": 1494.539175487284, "max": 1576.1815326925348, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 273747.77358766936, "min": 148491.1755175332, "max": 336654.3063271615, "count": 500 }, "SoccerTwos.Step.mean": { "value": 24999978.0, "min": 20009991.0, "max": 24999978.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 24999978.0, "min": 20009991.0, "max": 24999978.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01763874664902687, "min": -0.10776752978563309, "max": 0.07479347288608551, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.086780548095703, "min": -17.547164916992188, "max": 12.565303802490234, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01813901588320732, "min": -0.11023017019033432, "max": 0.0698384940624237, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.174327850341797, "min": -18.204742431640625, "max": 11.732867240905762, "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": 0.0786628542627607, "min": -0.34376484986507533, "max": 0.4665142857298559, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.765999495983124, "min": -59.32819986343384, "max": 47.49799942970276, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0786628542627607, "min": -0.34376484986507533, "max": 0.4665142857298559, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.765999495983124, "min": -59.32819986343384, "max": 47.49799942970276, "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": 0.01652876395867982, "min": 0.013891844534009578, "max": 0.023010420791979413, "count": 121 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01652876395867982, "min": 0.013891844534009578, "max": 0.023010420791979413, "count": 121 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10607224243382612, "min": 0.08422205423315367, "max": 0.1170943199346463, "count": 121 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10607224243382612, "min": 0.08422205423315367, "max": 0.1170943199346463, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10775665591160456, "min": 0.08507357910275459, "max": 0.11834435512622198, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10775665591160456, "min": 0.08507357910275459, "max": 0.11834435512622198, "count": 121 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 121 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00010000000000000003, "min": 0.00010000000000000003, "max": 0.00010000000000000003, "count": 121 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 121 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 121 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 121 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 121 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675995123", "python_version": "3.9.16 (main, Feb 6 2023, 20:06:40) \n[GCC 9.3.0]", "command_line_arguments": "/usr/bin/mlagents-learn ./config/poca/SoccerTwos_v4.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1676016142" }, "total": 21019.160699600005, "count": 1, "self": 0.4239419000223279, "children": { "run_training.setup": { "total": 0.02791030000662431, "count": 1, "self": 0.02791030000662431 }, "TrainerController.start_learning": { "total": 21018.708847399976, "count": 1, "self": 12.252090293797664, "children": { "TrainerController._reset_env": { "total": 1.578472400084138, "count": 21, "self": 1.578472400084138 }, "TrainerController.advance": { "total": 21004.07154440612, "count": 346217, "self": 13.339027916430496, "children": { "env_step": { "total": 11195.647434503247, "count": 346217, "self": 9608.978213496332, "children": { "SubprocessEnvManager._take_step": { "total": 1579.37136202713, "count": 346217, "self": 65.21483358863043, "children": { "TorchPolicy.evaluate": { "total": 1514.1565284384997, "count": 627082, "self": 1514.1565284384997 } } }, "workers": { "total": 7.297858979785815, "count": 346217, "self": 0.0, "children": { "worker_root": { "total": 20991.833144892298, "count": 346217, "is_parallel": true, "self": 12627.482296909031, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004215100023429841, "count": 2, "is_parallel": true, "self": 0.0011841999948956072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030309000285342336, "count": 8, "is_parallel": true, "self": 0.0030309000285342336 } } }, "UnityEnvironment.step": { "total": 0.034806600015144795, "count": 1, "is_parallel": true, "self": 0.0005694999708794057, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045980000868439674, "count": 1, "is_parallel": true, "self": 0.00045980000868439674 }, "communicator.exchange": { "total": 0.032166399993002415, "count": 1, "is_parallel": true, "self": 0.032166399993002415 }, "steps_from_proto": { "total": 0.001610900042578578, "count": 2, "is_parallel": true, "self": 0.00036669994005933404, "children": { "_process_rank_one_or_two_observation": { "total": 0.001244200102519244, "count": 8, "is_parallel": true, "self": 0.001244200102519244 } } } } } } }, "steps_from_proto": { "total": 0.04493440012447536, "count": 40, "is_parallel": true, "self": 0.009977000067010522, "children": { "_process_rank_one_or_two_observation": { "total": 0.03495740005746484, "count": 160, "is_parallel": true, "self": 0.03495740005746484 } } }, "UnityEnvironment.step": { "total": 8364.305913583143, "count": 346216, "is_parallel": true, "self": 273.51644306909293, "children": { "UnityEnvironment._generate_step_input": { "total": 217.13113000715384, "count": 346216, "is_parallel": true, "self": 217.13113000715384 }, "communicator.exchange": { "total": 7046.747987709532, "count": 346216, "is_parallel": true, "self": 7046.747987709532 }, "steps_from_proto": { "total": 826.9103527973639, "count": 692432, "is_parallel": true, "self": 182.80608186731115, "children": { "_process_rank_one_or_two_observation": { "total": 644.1042709300527, "count": 2769728, "is_parallel": true, "self": 644.1042709300527 } } } } } } } } } } }, "trainer_advance": { "total": 9795.085081986443, "count": 346217, "self": 69.57300218037562, "children": { "process_trajectory": { "total": 1763.8578488061903, "count": 346217, "self": 1761.022810106224, "children": { "RLTrainer._checkpoint": { "total": 2.8350386999663897, "count": 10, "self": 2.8350386999663897 } } }, "_update_policy": { "total": 7961.654230999877, "count": 121, "self": 920.4508470981964, "children": { "TorchPOCAOptimizer.update": { "total": 7041.20338390168, "count": 7260, "self": 7041.20338390168 } } } } } } }, "trainer_threads": { "total": 2.4999608285725117e-06, "count": 1, "self": 2.4999608285725117e-06 }, "TrainerController._save_models": { "total": 0.8067378000123426, "count": 1, "self": 0.00272019999101758, "children": { "RLTrainer._checkpoint": { "total": 0.804017600021325, "count": 1, "self": 0.804017600021325 } } } } } } }