{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6004561185836792, "min": 1.5689618587493896, "max": 3.295738697052002, "count": 1024 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30831.1875, "min": 28175.873046875, "max": 130293.6328125, "count": 1024 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.30555555555556, "min": 41.49152542372882, "max": 999.0, "count": 1024 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19672.0, "min": 12472.0, "max": 26544.0, "count": 1024 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1652.450874411084, "min": 1198.639780578417, "max": 1658.6088839985746, "count": 1006 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237952.9259151961, "min": 2397.279561156834, "max": 375913.0378456756, "count": 1006 }, "SoccerTwos.Step.mean": { "value": 10239970.0, "min": 9208.0, "max": 10239970.0, "count": 1024 }, "SoccerTwos.Step.sum": { "value": 10239970.0, "min": 9208.0, "max": 10239970.0, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016233595088124275, "min": -0.11867652088403702, "max": 0.14858490228652954, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.3376376628875732, "min": -25.562240600585938, "max": 24.890968322753906, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01581796631217003, "min": -0.11802703142166138, "max": 0.14724300801753998, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.277787208557129, "min": -25.596546173095703, "max": 24.887928009033203, "count": 1024 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1024 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.032191665636168584, "min": -0.5714285714285714, "max": 0.5155400015413761, "count": 1024 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.635599851608276, "min": -58.455799877643585, "max": 55.565599858760834, "count": 1024 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.032191665636168584, "min": -0.5714285714285714, "max": 0.5155400015413761, "count": 1024 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.635599851608276, "min": -58.455799877643585, "max": 55.565599858760834, "count": 1024 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1024 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1024 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019603986079649378, "min": 0.009950978774577379, "max": 0.025017476819145183, "count": 494 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019603986079649378, "min": 0.009950978774577379, "max": 0.025017476819145183, "count": 494 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08428130572040876, "min": 8.73256238567895e-06, "max": 0.12897534494598706, "count": 494 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08428130572040876, "min": 8.73256238567895e-06, "max": 0.12897534494598706, "count": 494 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08536892284949621, "min": 8.60937705814043e-06, "max": 0.13150523404280345, "count": 494 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08536892284949621, "min": 8.60937705814043e-06, "max": 0.13150523404280345, "count": 494 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 494 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 494 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 494 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 494 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 494 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 494 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677796003", "python_version": "3.9.16 (main, Mar 1 2023, 18:30:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Dtoma\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1677842865" }, "total": 46862.5396648, "count": 1, "self": 2.5128371999962837, "children": { "run_training.setup": { "total": 0.15924870000000002, "count": 1, "self": 0.15924870000000002 }, "TrainerController.start_learning": { "total": 46859.867578900004, "count": 1, "self": 20.798509800530155, "children": { "TrainerController._reset_env": { "total": 7.358011199997971, "count": 52, "self": 7.358011199997971 }, "TrainerController.advance": { "total": 46831.613211199474, "count": 704830, "self": 22.408079000124417, "children": { "env_step": { "total": 17365.559516898127, "count": 704830, "self": 13911.356851894923, "children": { "SubprocessEnvManager._take_step": { "total": 3440.487492101329, "count": 704830, "self": 128.03230620016757, "children": { "TorchPolicy.evaluate": { "total": 3312.4551859011613, "count": 1289232, "self": 3312.4551859011613 } } }, "workers": { "total": 13.715172901875253, "count": 704830, "self": 0.0, "children": { "worker_root": { "total": 46813.56796740158, "count": 704830, "is_parallel": true, "self": 35404.89834589947, "children": { "steps_from_proto": { "total": 0.12525900000167578, "count": 104, "is_parallel": true, "self": 0.028831699977910574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0964273000237652, "count": 416, "is_parallel": true, "self": 0.0964273000237652 } } }, "UnityEnvironment.step": { "total": 11408.544362502105, "count": 704830, "is_parallel": true, "self": 627.7944330064365, "children": { "UnityEnvironment._generate_step_input": { "total": 597.4331059980443, "count": 704830, "is_parallel": true, "self": 597.4331059980443 }, "communicator.exchange": { "total": 8147.493739900348, "count": 704830, "is_parallel": true, "self": 8147.493739900348 }, "steps_from_proto": { "total": 2035.8230835972754, "count": 1409660, "is_parallel": true, "self": 407.1948481040845, "children": { "_process_rank_one_or_two_observation": { "total": 1628.628235493191, "count": 5638640, "is_parallel": true, "self": 1628.628235493191 } } } } } } } } } } }, "trainer_advance": { "total": 29443.645615301222, "count": 704830, "self": 140.8990603024613, "children": { "process_trajectory": { "total": 4343.400427598707, "count": 704830, "self": 4339.3005863987055, "children": { "RLTrainer._checkpoint": { "total": 4.0998412000021744, "count": 20, "self": 4.0998412000021744 } } }, "_update_policy": { "total": 24959.346127400055, "count": 495, "self": 1915.2646575000763, "children": { "TorchPOCAOptimizer.update": { "total": 23044.08146989998, "count": 14830, "self": 23044.08146989998 } } } } } } }, "TrainerController._save_models": { "total": 0.0978467000022647, "count": 1, "self": 4.020000051241368e-05, "children": { "RLTrainer._checkpoint": { "total": 0.09780650000175228, "count": 1, "self": 0.09780650000175228 } } } } } } }