{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.295736312866211, "min": 3.295736312866211, "max": 3.295736312866211, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105463.5625, "min": 105463.5625, "max": 105463.5625, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 847.125, "min": 847.125, "max": 847.125, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 27108.0, "min": 27108.0, "max": 27108.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.7535925691843, "min": 1198.7535925691843, "max": 1198.7535925691843, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4795.014370276737, "min": 4795.014370276737, "max": 4795.014370276737, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9570.0, "min": 9570.0, "max": 9570.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9570.0, "min": 9570.0, "max": 9570.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09803476929664612, "min": -0.09803476929664612, "max": -0.09803476929664612, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.1764172315597534, "min": -1.1764172315597534, "max": -1.1764172315597534, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09807959198951721, "min": -0.09807959198951721, "max": -0.09807959198951721, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.1769551038742065, "min": -1.1769551038742065, "max": -1.1769551038742065, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3333333333333333, "min": -0.3333333333333333, "max": -0.3333333333333333, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0, "min": -4.0, "max": -4.0, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3333333333333333, "min": -0.3333333333333333, "max": -0.3333333333333333, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0, "min": -4.0, "max": -4.0, "count": 1 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688918279", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Carlos\\anaconda3\\envs\\rl\\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": "1688918309" }, "total": 29.512574500000003, "count": 1, "self": 0.257017500000007, "children": { "run_training.setup": { "total": 0.12948039999999983, "count": 1, "self": 0.12948039999999983 }, "TrainerController.start_learning": { "total": 29.126076599999998, "count": 1, "self": 0.020965799999949297, "children": { "TrainerController._reset_env": { "total": 3.7492373000000003, "count": 1, "self": 3.7492373000000003 }, "TrainerController.advance": { "total": 25.224098800000053, "count": 1002, "self": 0.02472750000005064, "children": { "env_step": { "total": 20.44633760000002, "count": 1002, "self": 16.403553900000006, "children": { "SubprocessEnvManager._take_step": { "total": 4.026453600000006, "count": 1002, "self": 0.15823190000002274, "children": { "TorchPolicy.evaluate": { "total": 3.8682216999999834, "count": 2000, "self": 3.8682216999999834 } } }, "workers": { "total": 0.016330100000009118, "count": 1002, "self": 0.0, "children": { "worker_root": { "total": 21.11746979999998, "count": 1002, "is_parallel": true, "self": 7.850120100000037, "children": { "steps_from_proto": { "total": 0.001739500000000227, "count": 2, "is_parallel": true, "self": 0.00032630000000022363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014132000000000033, "count": 8, "is_parallel": true, "self": 0.0014132000000000033 } } }, "UnityEnvironment.step": { "total": 13.265610199999944, "count": 1002, "is_parallel": true, "self": 0.6699475999999756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.671759100000008, "count": 1002, "is_parallel": true, "self": 0.671759100000008 }, "communicator.exchange": { "total": 10.034984099999917, "count": 1002, "is_parallel": true, "self": 10.034984099999917 }, "steps_from_proto": { "total": 1.8889194000000438, "count": 2004, "is_parallel": true, "self": 0.36631839999999816, "children": { "_process_rank_one_or_two_observation": { "total": 1.5226010000000456, "count": 8016, "is_parallel": true, "self": 1.5226010000000456 } } } } } } } } } } }, "trainer_advance": { "total": 4.753033699999981, "count": 1002, "self": 0.12693389999996718, "children": { "process_trajectory": { "total": 4.626099800000014, "count": 1002, "self": 4.626099800000014 } } } } }, "trainer_threads": { "total": 9.999999974752427e-07, "count": 1, "self": 9.999999974752427e-07 }, "TrainerController._save_models": { "total": 0.13177369999999655, "count": 1, "self": 4.100000000306636e-05, "children": { "RLTrainer._checkpoint": { "total": 0.13173269999999349, "count": 1, "self": 0.13173269999999349 } } } } } } }