{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6874216794967651, "min": 1.6478016376495361, "max": 3.295677900314331, "count": 951 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33856.4296875, "min": 18482.0703125, "max": 128380.6875, "count": 951 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 42.56896551724138, "min": 37.33846153846154, "max": 999.0, "count": 951 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19752.0, "min": 16160.0, "max": 23820.0, "count": 951 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1609.6513871239508, "min": 1193.9944345413408, "max": 1615.1674903382159, "count": 882 }, "SoccerTwos.Self-play.ELO.sum": { "value": 373439.1218127566, "min": 2389.2509810872843, "max": 412591.8287152013, "count": 882 }, "SoccerTwos.Step.mean": { "value": 9509952.0, "min": 9514.0, "max": 9509952.0, "count": 951 }, "SoccerTwos.Step.sum": { "value": 9509952.0, "min": 9514.0, "max": 9509952.0, "count": 951 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.05862795561552048, "min": -0.13394825160503387, "max": 0.14135195314884186, "count": 951 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 13.543057441711426, "min": -28.798873901367188, "max": 26.13471221923828, "count": 951 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0579887256026268, "min": -0.13388213515281677, "max": 0.1456393301486969, "count": 951 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 13.395395278930664, "min": -28.78466033935547, "max": 27.08891487121582, "count": 951 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 951 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 951 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.025980087069721967, "min": -0.548499995470047, "max": 0.4807999976750078, "count": 951 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.001400113105774, "min": -73.0988005399704, "max": 56.06800019741058, "count": 951 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.025980087069721967, "min": -0.548499995470047, "max": 0.4807999976750078, "count": 951 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.001400113105774, "min": -73.0988005399704, "max": 56.06800019741058, "count": 951 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 951 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 951 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01799885977137213, "min": 0.01121659071262305, "max": 0.026654944910357397, "count": 455 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01799885977137213, "min": 0.01121659071262305, "max": 0.026654944910357397, "count": 455 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12558400109410287, "min": 8.474503516708864e-07, "max": 0.13477052375674248, "count": 455 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12558400109410287, "min": 8.474503516708864e-07, "max": 0.13477052375674248, "count": 455 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.128904639929533, "min": 6.049062288108568e-07, "max": 0.13767754584550856, "count": 455 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.128904639929533, "min": 6.049062288108568e-07, "max": 0.13767754584550856, "count": 455 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 455 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 455 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 455 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 455 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 455 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 455 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689692865", "python_version": "3.9.0 (tags/v3.9.0:9cf6752, Oct 5 2020, 15:34:40) [MSC v.1927 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\82103\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.27.0", "mlagents_envs_version": "0.27.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.4", "end_time_seconds": "1689767834" }, "total": 74968.6432839, "count": 1, "self": 1.0722764000092866, "children": { "run_training.setup": { "total": 0.21628860000000039, "count": 1, "self": 0.21628860000000039 }, "TrainerController.start_learning": { "total": 74967.3547189, "count": 1, "self": 16.29819830370252, "children": { "TrainerController._reset_env": { "total": 18.226340000011916, "count": 48, "self": 18.226340000011916 }, "TrainerController.advance": { "total": 74932.46589879629, "count": 651619, "self": 18.065950498581515, "children": { "env_step": { "total": 65539.21146319895, "count": 651619, "self": 58316.224652403274, "children": { "SubprocessEnvManager._take_step": { "total": 7212.91181029586, "count": 651619, "self": 98.26668139424874, "children": { "TorchPolicy.evaluate": { "total": 7114.645128901611, "count": 1204082, "self": 2158.299612108486, "children": { "TorchPolicy.sample_actions": { "total": 4956.345516793125, "count": 1204082, "self": 4956.345516793125 } } } } }, "workers": { "total": 10.075000499819065, "count": 651618, "self": 0.0, "children": { "worker_root": { "total": 74930.87029240122, "count": 651618, "is_parallel": true, "self": 18445.115230901356, "children": { "steps_from_proto": { "total": 0.10292970002329183, "count": 96, "is_parallel": true, "self": 0.01933739998072337, "children": { "_process_rank_one_or_two_observation": { "total": 0.08359230004256846, "count": 384, "is_parallel": true, "self": 0.08359230004256846 } } }, "UnityEnvironment.step": { "total": 56485.65213179984, "count": 651618, "is_parallel": true, "self": 150.65997370121477, "children": { "UnityEnvironment._generate_step_input": { "total": 1047.3210755980285, "count": 651618, "is_parallel": true, "self": 1047.3210755980285 }, "communicator.exchange": { "total": 53626.6576641021, "count": 651618, "is_parallel": true, "self": 53626.6576641021 }, "steps_from_proto": { "total": 1661.0134183985028, "count": 1303236, "is_parallel": true, "self": 300.7723709046502, "children": { "_process_rank_one_or_two_observation": { "total": 1360.2410474938526, "count": 5212944, "is_parallel": true, "self": 1360.2410474938526 } } } } } } } } } } }, "trainer_advance": { "total": 9375.188485098752, "count": 651618, "self": 107.77188799596843, "children": { "process_trajectory": { "total": 4311.11645370272, "count": 651618, "self": 4304.69812200271, "children": { "RLTrainer._checkpoint": { "total": 6.41833170000973, "count": 19, "self": 6.41833170000973 } } }, "_update_policy": { "total": 4956.3001434000635, "count": 456, "self": 1371.0768024994582, "children": { "TorchPOCAOptimizer.update": { "total": 3585.2233409006053, "count": 13680, "self": 3585.2233409006053 } } } } } } }, "trainer_threads": { "total": 1.2999953469261527e-06, "count": 1, "self": 1.2999953469261527e-06 }, "TrainerController._save_models": { "total": 0.36428049999813084, "count": 1, "self": 0.03878580000309739, "children": { "RLTrainer._checkpoint": { "total": 0.32549469999503344, "count": 1, "self": 0.32549469999503344 } } } } } } }