{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1891121864318848, "min": 3.1891121864318848, "max": 3.2957725524902344, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38371.3984375, "min": 33133.1484375, "max": 105464.703125, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 694.5, "min": 369.7857142857143, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16668.0, "min": 16296.0, "max": 23180.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1190.1647140632276, "min": 1186.7377343620822, "max": 1199.0826549241756, "count": 46 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7140.988284379366, "min": 2375.726828196862, "max": 19072.774282540555, "count": 46 }, "SoccerTwos.Step.mean": { "value": 499970.0, "min": 9466.0, "max": 499970.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499970.0, "min": 9466.0, "max": 499970.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0017046892317011952, "min": -0.0035901349037885666, "max": 0.039336107671260834, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.02045627124607563, "min": -0.06291120499372482, "max": 0.7080499529838562, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0020592056680470705, "min": -0.004296165890991688, "max": 0.039406679570674896, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.02471046894788742, "min": -0.0714874118566513, "max": 0.709248423576355, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.14760000010331473, "min": -0.631578947368421, "max": 0.16383333007494608, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.7712000012397766, "min": -12.0, "max": 2.0527999997138977, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.14760000010331473, "min": -0.631578947368421, "max": 0.16383333007494608, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.7712000012397766, "min": -12.0, "max": 2.0527999997138977, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01596044124908076, "min": 0.013050664076581597, "max": 0.02100246695384461, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01596044124908076, "min": 0.013050664076581597, "max": 0.02100246695384461, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0007662195588636677, "min": 1.7274955496304757e-06, "max": 0.0088959782384336, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0007662195588636677, "min": 1.7274955496304757e-06, "max": 0.0088959782384336, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007670570633005506, "min": 2.533634021043933e-06, "max": 0.008333718854313095, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007670570633005506, "min": 2.533634021043933e-06, "max": 0.008333718854313095, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677334642", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/jeremyroth/opt/anaconda3/envs/RLv3/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/mlagents/training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1677336712" }, "total": 2070.668378083, "count": 1, "self": 0.64610783299986, "children": { "run_training.setup": { "total": 0.04077541600000245, "count": 1, "self": 0.04077541600000245 }, "TrainerController.start_learning": { "total": 2069.981494834, "count": 1, "self": 0.4126531790111585, "children": { "TrainerController._reset_env": { "total": 6.270773749999972, "count": 3, "self": 6.270773749999972 }, "TrainerController.advance": { "total": 2063.1949332789886, "count": 32467, "self": 0.4099314669933847, "children": { "env_step": { "total": 477.554740902993, "count": 32467, "self": 392.21695004399317, "children": { "SubprocessEnvManager._take_step": { "total": 85.05494806301418, "count": 32467, "self": 2.208190647045271, "children": { "TorchPolicy.evaluate": { "total": 82.84675741596891, "count": 64372, "self": 82.84675741596891 } } }, "workers": { "total": 0.2828427959856725, "count": 32467, "self": 0.0, "children": { "worker_root": { "total": 2062.9050869500093, "count": 32467, "is_parallel": true, "self": 1724.3547209240162, "children": { "steps_from_proto": { "total": 0.005384292000291779, "count": 6, "is_parallel": true, "self": 0.0012170820005117378, "children": { "_process_rank_one_or_two_observation": { "total": 0.004167209999780042, "count": 24, "is_parallel": true, "self": 0.004167209999780042 } } }, "UnityEnvironment.step": { "total": 338.5449817339927, "count": 32467, "is_parallel": true, "self": 14.070085187980112, "children": { "UnityEnvironment._generate_step_input": { "total": 9.744495356989887, "count": 32467, "is_parallel": true, "self": 9.744495356989887 }, "communicator.exchange": { "total": 270.3217709160027, "count": 32467, "is_parallel": true, "self": 270.3217709160027 }, "steps_from_proto": { "total": 44.40863027301996, "count": 64934, "is_parallel": true, "self": 7.347313958017516, "children": { "_process_rank_one_or_two_observation": { "total": 37.06131631500244, "count": 259736, "is_parallel": true, "self": 37.06131631500244 } } } } } } } } } } }, "trainer_advance": { "total": 1585.2302609090025, "count": 32467, "self": 3.5265820750200874, "children": { "process_trajectory": { "total": 181.2961166259828, "count": 32467, "self": 181.16346316698298, "children": { "RLTrainer._checkpoint": { "total": 0.13265345899981185, "count": 1, "self": 0.13265345899981185 } } }, "_update_policy": { "total": 1400.4075622079997, "count": 23, "self": 58.88397164799903, "children": { "TorchPOCAOptimizer.update": { "total": 1341.5235905600007, "count": 690, "self": 1341.5235905600007 } } } } } } }, "trainer_threads": { "total": 5.420001798484009e-07, "count": 1, "self": 5.420001798484009e-07 }, "TrainerController._save_models": { "total": 0.1031340839999757, "count": 1, "self": 0.0006453759997384623, "children": { "RLTrainer._checkpoint": { "total": 0.10248870800023724, "count": 1, "self": 0.10248870800023724 } } } } } } }