{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.286545753479004, "min": 3.2799487113952637, "max": 3.2957255840301514, "count": 6 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55003.62890625, "min": 36448.6015625, "max": 105463.21875, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 781.8571428571429, "max": 999.0, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 13660.0, "max": 30168.0, "count": 6 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.205006106708, "min": 1199.5028730369677, "max": 1202.2305948025287, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2402.410012213416, "min": 2402.410012213416, "max": 7213.383568815172, "count": 5 }, "SoccerTwos.Step.mean": { "value": 59084.0, "min": 9100.0, "max": 59084.0, "count": 6 }, "SoccerTwos.Step.sum": { "value": 59084.0, "min": 9100.0, "max": 59084.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0017422193195670843, "min": -0.013540264219045639, "max": -0.0017422193195670843, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.01742219366133213, "min": -0.16248317062854767, "max": -0.01742219366133213, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0051831635646522045, "min": -0.013567925430834293, "max": -0.0051831635646522045, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.05183163657784462, "min": -0.16281510889530182, "max": -0.05183163657784462, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.2, "max": 0.09700000332668424, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -2.0, "max": 1.1640000399202108, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.2, "max": 0.09700000332668424, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -2.0, "max": 1.1640000399202108, "count": 6 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01165679257683223, "min": 0.01165679257683223, "max": 0.015404471598837214, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01165679257683223, "min": 0.01165679257683223, "max": 0.015404471598837214, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0019071170633348327, "min": 0.0015114257888247569, "max": 0.0019071170633348327, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0019071170633348327, "min": 0.0015114257888247569, "max": 0.0019071170633348327, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0019426810302926847, "min": 0.0012286341758832957, "max": 0.0019426810302926847, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0019426810302926847, "min": 0.0012286341758832957, "max": 0.0019426810302926847, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690795222", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\User\\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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1690795352" }, "total": 130.3720441, "count": 1, "self": 0.0733976999999868, "children": { "run_training.setup": { "total": 0.07721880000000003, "count": 1, "self": 0.07721880000000003 }, "TrainerController.start_learning": { "total": 130.22142760000003, "count": 1, "self": 0.10734660000059648, "children": { "TrainerController._reset_env": { "total": 2.4465953999999996, "count": 1, "self": 2.4465953999999996 }, "TrainerController.advance": { "total": 127.55914779999944, "count": 4454, "self": 0.10057499999965103, "children": { "env_step": { "total": 67.04976439999999, "count": 4454, "self": 48.87346289999975, "children": { "SubprocessEnvManager._take_step": { "total": 18.116562999999942, "count": 4454, "self": 0.5460334000005211, "children": { "TorchPolicy.evaluate": { "total": 17.57052959999942, "count": 8874, "self": 17.57052959999942 } } }, "workers": { "total": 0.05973850000029035, "count": 4454, "self": 0.0, "children": { "worker_root": { "total": 118.82038529999961, "count": 4454, "is_parallel": true, "self": 81.92932019999984, "children": { "steps_from_proto": { "total": 0.0010920999999997072, "count": 2, "is_parallel": true, "self": 0.00022529999999942874, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008668000000002785, "count": 8, "is_parallel": true, "self": 0.0008668000000002785 } } }, "UnityEnvironment.step": { "total": 36.889972999999785, "count": 4454, "is_parallel": true, "self": 1.9315163999990972, "children": { "UnityEnvironment._generate_step_input": { "total": 1.8743645000002829, "count": 4454, "is_parallel": true, "self": 1.8743645000002829 }, "communicator.exchange": { "total": 26.44697940000008, "count": 4454, "is_parallel": true, "self": 26.44697940000008 }, "steps_from_proto": { "total": 6.637112700000321, "count": 8908, "is_parallel": true, "self": 1.4580303000004573, "children": { "_process_rank_one_or_two_observation": { "total": 5.179082399999864, "count": 35632, "is_parallel": true, "self": 5.179082399999864 } } } } } } } } } } }, "trainer_advance": { "total": 60.4088083999998, "count": 4454, "self": 0.5503726000001663, "children": { "process_trajectory": { "total": 13.114336999999644, "count": 4454, "self": 13.114336999999644 }, "_update_policy": { "total": 46.74409879999999, "count": 3, "self": 7.118506999999994, "children": { "TorchPOCAOptimizer.update": { "total": 39.625591799999995, "count": 73, "self": 39.625591799999995 } } } } } } }, "trainer_threads": { "total": 5.999999928008037e-07, "count": 1, "self": 5.999999928008037e-07 }, "TrainerController._save_models": { "total": 0.10833719999999403, "count": 1, "self": 4.419999999072388e-05, "children": { "RLTrainer._checkpoint": { "total": 0.1082930000000033, "count": 1, "self": 0.1082930000000033 } } } } } } }