{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9742658138275146, "min": 1.9314336776733398, "max": 2.0035929679870605, "count": 15 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38221.78515625, "min": 32425.68359375, "max": 44507.77734375, "count": 15 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.63492063492063, "min": 55.35294117647059, "max": 91.49056603773585, "count": 15 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18556.0, "min": 14312.0, "max": 20800.0, "count": 15 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1379.7376955798372, "min": 1379.7376955798372, "max": 1412.1002824100194, "count": 15 }, "SoccerTwos.Self-play.ELO.sum": { "value": 173846.9496430595, "min": 147825.80077454436, "max": 237561.2835015751, "count": 15 }, "SoccerTwos.Step.mean": { "value": 6999974.0, "min": 6859993.0, "max": 6999974.0, "count": 15 }, "SoccerTwos.Step.sum": { "value": 6999974.0, "min": 6859993.0, "max": 6999974.0, "count": 15 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09554355591535568, "min": -0.09554355591535568, "max": 0.002206910867244005, "count": 15 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.134031295776367, "min": -12.695816993713379, "max": 0.29572606086730957, "count": 15 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09482166916131973, "min": -0.09482166916131973, "max": 0.004114869050681591, "count": 15 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -12.042351722717285, "min": -12.286849975585938, "max": 0.5513924360275269, "count": 15 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 15 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 15 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.20141259657116387, "min": -0.20141259657116387, "max": 0.13733928863491332, "count": 15 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.57939976453781, "min": -25.57939976453781, "max": 18.184399724006653, "count": 15 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.20141259657116387, "min": -0.20141259657116387, "max": 0.13733928863491332, "count": 15 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.57939976453781, "min": -25.57939976453781, "max": 18.184399724006653, "count": 15 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019305873146125425, "min": 0.01447424718887002, "max": 0.019305873146125425, "count": 7 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019305873146125425, "min": 0.01447424718887002, "max": 0.019305873146125425, "count": 7 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07701919426520666, "min": 0.07701919426520666, "max": 0.0907278207441171, "count": 7 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07701919426520666, "min": 0.07701919426520666, "max": 0.0907278207441171, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07767093007763227, "min": 0.07767093007763227, "max": 0.09189345066746075, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07767093007763227, "min": 0.07767093007763227, "max": 0.09189345066746075, "count": 7 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679662811", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Uou\\anaconda3\\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": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679663091" }, "total": 279.725273, "count": 1, "self": 0.20115229999998974, "children": { "run_training.setup": { "total": 0.08949819999999997, "count": 1, "self": 0.08949819999999997 }, "TrainerController.start_learning": { "total": 279.43462250000005, "count": 1, "self": 0.19731710000093017, "children": { "TrainerController._reset_env": { "total": 6.37954240000002, "count": 3, "self": 6.37954240000002 }, "TrainerController.advance": { "total": 272.75142099999914, "count": 10135, "self": 0.18591269999819815, "children": { "env_step": { "total": 119.06260349999917, "count": 10135, "self": 91.67096809999751, "children": { "SubprocessEnvManager._take_step": { "total": 27.27935460000083, "count": 10135, "self": 0.9209951999986004, "children": { "TorchPolicy.evaluate": { "total": 26.35835940000223, "count": 18664, "self": 26.35835940000223 } } }, "workers": { "total": 0.11228080000083729, "count": 10135, "self": 0.0, "children": { "worker_root": { "total": 272.6262865000011, "count": 10135, "is_parallel": true, "self": 199.86824730000032, "children": { "steps_from_proto": { "total": 0.004147999999988272, "count": 6, "is_parallel": true, "self": 0.0008679000000366699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032800999999516023, "count": 24, "is_parallel": true, "self": 0.0032800999999516023 } } }, "UnityEnvironment.step": { "total": 72.75389120000077, "count": 10135, "is_parallel": true, "self": 3.9121836999971435, "children": { "UnityEnvironment._generate_step_input": { "total": 3.1415486000000756, "count": 10135, "is_parallel": true, "self": 3.1415486000000756 }, "communicator.exchange": { "total": 52.90128760000205, "count": 10135, "is_parallel": true, "self": 52.90128760000205 }, "steps_from_proto": { "total": 12.798871300001489, "count": 20270, "is_parallel": true, "self": 2.618537500002743, "children": { "_process_rank_one_or_two_observation": { "total": 10.180333799998746, "count": 81080, "is_parallel": true, "self": 10.180333799998746 } } } } } } } } } } }, "trainer_advance": { "total": 153.50290480000177, "count": 10135, "self": 1.383309100002208, "children": { "process_trajectory": { "total": 26.531433299999538, "count": 10135, "self": 26.39065149999958, "children": { "RLTrainer._checkpoint": { "total": 0.14078179999995655, "count": 1, "self": 0.14078179999995655 } } }, "_update_policy": { "total": 125.58816240000002, "count": 7, "self": 18.430034399999542, "children": { "TorchPOCAOptimizer.update": { "total": 107.15812800000047, "count": 210, "self": 107.15812800000047 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.1063413999999625, "count": 1, "self": 0.006397299999946426, "children": { "RLTrainer._checkpoint": { "total": 0.09994410000001608, "count": 1, "self": 0.09994410000001608 } } } } } } }