{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8022698163986206, "min": 1.8022698163986206, "max": 1.8022698163986206, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 20646.802734375, "min": 20646.802734375, "max": 20646.802734375, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.61363636363637, "min": 52.61363636363637, "max": 52.61363636363637, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 9260.0, "min": 9260.0, "max": 9260.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1703.0449882685107, "min": 1703.0449882685107, "max": 1703.0449882685107, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 149867.95896762895, "min": 149867.95896762895, "max": 149867.95896762895, "count": 1 }, "SoccerTwos.Step.mean": { "value": 14399980.0, "min": 14399980.0, "max": 14399980.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 14399980.0, "min": 14399980.0, "max": 14399980.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.12761053442955017, "min": -0.12761053442955017, "max": -0.12761053442955017, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.974505424499512, "min": -10.974505424499512, "max": -10.974505424499512, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.12688703835010529, "min": -0.12688703835010529, "max": -0.12688703835010529, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.912284851074219, "min": -10.912284851074219, "max": -10.912284851074219, "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": -0.3230837209280147, "min": -0.3230837209280147, "max": -0.3230837209280147, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -27.785199999809265, "min": -27.785199999809265, "max": -27.785199999809265, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3230837209280147, "min": -0.3230837209280147, "max": -0.3230837209280147, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -27.785199999809265, "min": -27.785199999809265, "max": -27.785199999809265, "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": "1740246558", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/Rava/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0", "numpy_version": "1.23.5", "end_time_seconds": "1740246574" }, "total": 16.636009916997864, "count": 1, "self": 0.18583970901090652, "children": { "run_training.setup": { "total": 0.03656129199953284, "count": 1, "self": 0.03656129199953284 }, "TrainerController.start_learning": { "total": 16.413608915987425, "count": 1, "self": 0.002974370145238936, "children": { "TrainerController._reset_env": { "total": 1.857082791015273, "count": 2, "self": 1.857082791015273 }, "TrainerController.advance": { "total": 14.452344170829747, "count": 387, "self": 0.0027541567687876523, "children": { "env_step": { "total": 13.922965923979064, "count": 387, "self": 13.51434391582734, "children": { "SubprocessEnvManager._take_step": { "total": 0.40676737106696237, "count": 387, "self": 0.012269758910406381, "children": { "TorchPolicy.evaluate": { "total": 0.394497612156556, "count": 716, "self": 0.394497612156556 } } }, "workers": { "total": 0.0018546370847616345, "count": 387, "self": 0.0, "children": { "worker_root": { "total": 14.876430246149539, "count": 387, "is_parallel": true, "self": 1.7209492633846821, "children": { "steps_from_proto": { "total": 0.002650748996529728, "count": 4, "is_parallel": true, "self": 0.00036129201180301607, "children": { "_process_rank_one_or_two_observation": { "total": 0.002289456984726712, "count": 16, "is_parallel": true, "self": 0.002289456984726712 } } }, "UnityEnvironment.step": { "total": 13.152830233768327, "count": 387, "is_parallel": true, "self": 0.03488348981773015, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2457014889077982, "count": 387, "is_parallel": true, "self": 0.2457014889077982 }, "communicator.exchange": { "total": 12.421524163917638, "count": 387, "is_parallel": true, "self": 12.421524163917638 }, "steps_from_proto": { "total": 0.45072109112516046, "count": 774, "is_parallel": true, "self": 0.048481980338692665, "children": { "_process_rank_one_or_two_observation": { "total": 0.4022391107864678, "count": 3096, "is_parallel": true, "self": 0.4022391107864678 } } } } } } } } } } }, "trainer_advance": { "total": 0.5266240900818957, "count": 387, "self": 0.018710285075940192, "children": { "process_trajectory": { "total": 0.5079138050059555, "count": 387, "self": 0.5079138050059555 } } } } }, "trainer_threads": { "total": 2.9199873097240925e-07, "count": 1, "self": 2.9199873097240925e-07 }, "TrainerController._save_models": { "total": 0.10120729199843481, "count": 1, "self": 0.0005302920035319403, "children": { "RLTrainer._checkpoint": { "total": 0.10067699999490287, "count": 1, "self": 0.10067699999490287 } } } } } } }