{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0848796367645264, "min": 2.0848796367645264, "max": 2.0848796367645264, "count": 2 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41964.45703125, "min": 41964.45703125, "max": 41964.45703125, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 99.73170731707317, "min": 99.73170731707317, "max": 99.73170731707317, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16356.0, "min": 16356.0, "max": 16356.0, "count": 2 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1573.855320449373, "min": 1573.855320449373, "max": 1573.855320449373, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 129056.13627684859, "min": 129056.13627684859, "max": 129056.13627684859, "count": 2 }, "SoccerTwos.Step.mean": { "value": 15159963.0, "min": 15159963.0, "max": 15159963.0, "count": 2 }, "SoccerTwos.Step.sum": { "value": 15159963.0, "min": 15159963.0, "max": 15159963.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03139190748333931, "min": -0.03139190748333931, "max": -0.03139190748333931, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.5427446365356445, "min": -2.5427446365356445, "max": -2.5427446365356445, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03286875784397125, "min": -0.03286875784397125, "max": -0.03286875784397125, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.6623694896698, "min": -2.6623694896698, "max": -2.6623694896698, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11639506434216912, "min": -0.11639506434216912, "max": -0.11639506434216912, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.428000211715698, "min": -9.428000211715698, "max": -9.428000211715698, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11639506434216912, "min": -0.11639506434216912, "max": -0.11639506434216912, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.428000211715698, "min": -9.428000211715698, "max": -9.428000211715698, "count": 2 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691938828", "python_version": "3.8.17 (default, Aug 12 2023, 11:35:15) \n[GCC 12.2.0]", "command_line_arguments": "/home/rj/git/SoccerTwos-Experiment/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos2 --no-graphics --resume", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691938847" }, "total": 19.233548452000832, "count": 1, "self": 0.04269905399996787, "children": { "run_training.setup": { "total": 0.016969304000667762, "count": 1, "self": 0.016969304000667762 }, "TrainerController.start_learning": { "total": 19.173880094000197, "count": 1, "self": 0.01757897601419245, "children": { "TrainerController._reset_env": { "total": 2.5280304399966553, "count": 2, "self": 2.5280304399966553 }, "TrainerController.advance": { "total": 16.452380556991557, "count": 1042, "self": 0.016848541981744347, "children": { "env_step": { "total": 14.86173546901773, "count": 1042, "self": 11.586702440163208, "children": { "SubprocessEnvManager._take_step": { "total": 3.2640924369152344, "count": 1042, "self": 0.08654742198632448, "children": { "TorchPolicy.evaluate": { "total": 3.17754501492891, "count": 1976, "self": 3.17754501492891 } } }, "workers": { "total": 0.010940591939288424, "count": 1042, "self": 0.0, "children": { "worker_root": { "total": 18.973768526062486, "count": 1042, "is_parallel": true, "self": 9.374608403035381, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018578439994598739, "count": 2, "is_parallel": true, "self": 0.0004488080012379214, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014090359982219525, "count": 8, "is_parallel": true, "self": 0.0014090359982219525 } } }, "UnityEnvironment.step": { "total": 0.01887377000093693, "count": 1, "is_parallel": true, "self": 0.0003956840046157595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003201449981133919, "count": 1, "is_parallel": true, "self": 0.0003201449981133919 }, "communicator.exchange": { "total": 0.01677491100053885, "count": 1, "is_parallel": true, "self": 0.01677491100053885 }, "steps_from_proto": { "total": 0.0013830299976689275, "count": 2, "is_parallel": true, "self": 0.00027834899447043426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011046810031984933, "count": 8, "is_parallel": true, "self": 0.0011046810031984933 } } } } } } }, "steps_from_proto": { "total": 0.0014911150028638076, "count": 2, "is_parallel": true, "self": 0.00028380099684000015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012073140060238075, "count": 8, "is_parallel": true, "self": 0.0012073140060238075 } } }, "UnityEnvironment.step": { "total": 9.59766900802424, "count": 1041, "is_parallel": true, "self": 0.467117640102515, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2962214838989894, "count": 1041, "is_parallel": true, "self": 0.2962214838989894 }, "communicator.exchange": { "total": 7.481069154087891, "count": 1041, "is_parallel": true, "self": 7.481069154087891 }, "steps_from_proto": { "total": 1.3532607299348456, "count": 2082, "is_parallel": true, "self": 0.2788171200081706, "children": { "_process_rank_one_or_two_observation": { "total": 1.074443609926675, "count": 8328, "is_parallel": true, "self": 1.074443609926675 } } } } } } } } } } }, "trainer_advance": { "total": 1.5737965459920815, "count": 1042, "self": 0.09985104594670702, "children": { "process_trajectory": { "total": 1.4739455000453745, "count": 1042, "self": 1.4739455000453745 } } } } }, "trainer_threads": { "total": 8.589995559304953e-07, "count": 1, "self": 8.589995559304953e-07 }, "TrainerController._save_models": { "total": 0.17588926199823618, "count": 1, "self": 0.0018678550004551653, "children": { "RLTrainer._checkpoint": { "total": 0.17402140699778101, "count": 1, "self": 0.17402140699778101 } } } } } } }