{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5664501190185547, "min": 1.3704438209533691, "max": 3.2957327365875244, "count": 4100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32682.4140625, "min": 23880.1640625, "max": 105463.390625, "count": 4100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.68674698795181, "min": 40.17213114754098, "max": 999.0, "count": 4100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19484.0, "min": 12740.0, "max": 27856.0, "count": 4100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1713.0888068764343, "min": 1190.2701234025049, "max": 1784.2425878785427, "count": 4090 }, "SoccerTwos.Self-play.ELO.sum": { "value": 284372.7419414881, "min": 2390.22406688933, "max": 412353.9496239149, "count": 4090 }, "SoccerTwos.Step.mean": { "value": 40999948.0, "min": 9946.0, "max": 40999948.0, "count": 4100 }, "SoccerTwos.Step.sum": { "value": 40999948.0, "min": 9946.0, "max": 40999948.0, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.053514398634433746, "min": -0.14564241468906403, "max": 0.1744980812072754, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.883390426635742, "min": -25.556011199951172, "max": 27.406518936157227, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05552731454372406, "min": -0.14718903601169586, "max": 0.17098216712474823, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.217534065246582, "min": -26.635845184326172, "max": 27.209861755371094, "count": 4100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.027815663670919026, "min": -0.631578947368421, "max": 0.5439741899890285, "count": 4100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.617400169372559, "min": -67.63940012454987, "max": 75.96959972381592, "count": 4100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.027815663670919026, "min": -0.631578947368421, "max": 0.5439741899890285, "count": 4100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.617400169372559, "min": -67.63940012454987, "max": 75.96959972381592, "count": 4100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.023335595968334625, "min": 0.009787198154178138, "max": 0.026557448925450443, "count": 1987 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023335595968334625, "min": 0.009787198154178138, "max": 0.026557448925450443, "count": 1987 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08541073525945346, "min": 0.00032363719219574705, "max": 0.12670950815081597, "count": 1987 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08541073525945346, "min": 0.00032363719219574705, "max": 0.12670950815081597, "count": 1987 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08672901342312495, "min": 0.0003287055459319769, "max": 0.12981149380405743, "count": 1987 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08672901342312495, "min": 0.0003287055459319769, "max": 0.12981149380405743, "count": 1987 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1987 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1987 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1987 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1987 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1987 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1987 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718818667", "python_version": "3.10.10 (tags/v3.10.10:aad5f6a, Feb 7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "c:\\Users\\wvfir\\Desktop\\hfcode\\.venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1718879999" }, "total": 61331.52861019998, "count": 1, "self": 0.005198600003495812, "children": { "run_training.setup": { "total": 0.05639869999140501, "count": 1, "self": 0.05639869999140501 }, "TrainerController.start_learning": { "total": 61331.467012899986, "count": 1, "self": 33.73559428541921, "children": { "TrainerController._reset_env": { "total": 4.656778900302015, "count": 103, "self": 4.656778900302015 }, "TrainerController.advance": { "total": 61292.988029514265, "count": 2821662, "self": 28.642768405436072, "children": { "env_step": { "total": 26406.1796775306, "count": 2821662, "self": 21577.762173053576, "children": { "SubprocessEnvManager._take_step": { "total": 4806.036467085942, "count": 2821662, "self": 187.59450200403808, "children": { "TorchPolicy.evaluate": { "total": 4618.441965081904, "count": 5137530, "self": 4618.441965081904 } } }, "workers": { "total": 22.381037391081918, "count": 2821662, "self": 0.0, "children": { "worker_root": { "total": 61277.90901889966, "count": 2821662, "is_parallel": true, "self": 43550.35270983534, "children": { "steps_from_proto": { "total": 0.09858030080795288, "count": 206, "is_parallel": true, "self": 0.01813820016104728, "children": { "_process_rank_one_or_two_observation": { "total": 0.0804421006469056, "count": 824, "is_parallel": true, "self": 0.0804421006469056 } } }, "UnityEnvironment.step": { "total": 17727.45772876352, "count": 2821662, "is_parallel": true, "self": 690.9482741361135, "children": { "UnityEnvironment._generate_step_input": { "total": 511.4682991858572, "count": 2821662, "is_parallel": true, "self": 511.4682991858572 }, "communicator.exchange": { "total": 14317.233451196866, "count": 2821662, "is_parallel": true, "self": 14317.233451196866 }, "steps_from_proto": { "total": 2207.807704244682, "count": 5643324, "is_parallel": true, "self": 398.33461867959704, "children": { "_process_rank_one_or_two_observation": { "total": 1809.473085565085, "count": 22573296, "is_parallel": true, "self": 1809.473085565085 } } } } } } } } } } }, "trainer_advance": { "total": 34858.16558357823, "count": 2821662, "self": 344.269853744132, "children": { "process_trajectory": { "total": 5836.778495934326, "count": 2821662, "self": 5830.233406834828, "children": { "RLTrainer._checkpoint": { "total": 6.545089099498, "count": 82, "self": 6.545089099498 } } }, "_update_policy": { "total": 28677.11723389977, "count": 1988, "self": 2849.294930687931, "children": { "TorchPOCAOptimizer.update": { "total": 25827.82230321184, "count": 59617, "self": 25827.82230321184 } } } } } } }, "trainer_threads": { "total": 6.00004568696022e-07, "count": 1, "self": 6.00004568696022e-07 }, "TrainerController._save_models": { "total": 0.08660959999542683, "count": 1, "self": 0.0032872000010684133, "children": { "RLTrainer._checkpoint": { "total": 0.08332239999435842, "count": 1, "self": 0.08332239999435842 } } } } } } }