{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.295736312866211, "min": 3.295736312866211, "max": 3.295736312866211, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105463.5625, "min": 105463.5625, "max": 105463.5625, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 814.0, "min": 814.0, "max": 814.0, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 26048.0, "min": 26048.0, "max": 26048.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.862184640307, "min": 1198.862184640307, "max": 1198.862184640307, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11988.62184640307, "min": 11988.62184640307, "max": 11988.62184640307, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9040.0, "min": 9040.0, "max": 9040.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9040.0, "min": 9040.0, "max": 9040.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0657878965139389, "min": -0.0657878965139389, "max": -0.0657878965139389, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7894547581672668, "min": -0.7894547581672668, "max": -0.7894547581672668, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0656895861029625, "min": -0.0656895861029625, "max": -0.0656895861029625, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7882750034332275, "min": -0.7882750034332275, "max": -0.7882750034332275, "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": -0.42826666434605914, "min": -0.42826666434605914, "max": -0.42826666434605914, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.13919997215271, "min": -5.13919997215271, "max": -5.13919997215271, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.42826666434605914, "min": -0.42826666434605914, "max": -0.42826666434605914, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.13919997215271, "min": -5.13919997215271, "max": -5.13919997215271, "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": "1677487363", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos-2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1677487418" }, "total": 55.495356125, "count": 1, "self": 0.2339272500000007, "children": { "run_training.setup": { "total": 0.013540665999999923, "count": 1, "self": 0.013540665999999923 }, "TrainerController.start_learning": { "total": 55.247888209, "count": 1, "self": 0.011354460000163158, "children": { "TrainerController._reset_env": { "total": 2.1705418749999996, "count": 1, "self": 2.1705418749999996 }, "TrainerController.advance": { "total": 52.93329379099985, "count": 1078, "self": 0.009603352999853598, "children": { "env_step": { "total": 51.50809744300005, "count": 1078, "self": 49.850218249000115, "children": { "SubprocessEnvManager._take_step": { "total": 1.6496916149999485, "count": 1078, "self": 0.046530256999989916, "children": { "TorchPolicy.evaluate": { "total": 1.6031613579999586, "count": 2152, "self": 1.6031613579999586 } } }, "workers": { "total": 0.00818757899998257, "count": 1077, "self": 0.0, "children": { "worker_root": { "total": 52.971644691999956, "count": 1077, "is_parallel": true, "self": 4.477422349999976, "children": { "steps_from_proto": { "total": 0.001703250000000267, "count": 2, "is_parallel": true, "self": 0.00023233399999966764, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014709160000005994, "count": 8, "is_parallel": true, "self": 0.0014709160000005994 } } }, "UnityEnvironment.step": { "total": 48.49251909199998, "count": 1077, "is_parallel": true, "self": 0.13511654599970058, "children": { "UnityEnvironment._generate_step_input": { "total": 0.902806952999998, "count": 1077, "is_parallel": true, "self": 0.902806952999998 }, "communicator.exchange": { "total": 45.52362824600006, "count": 1077, "is_parallel": true, "self": 45.52362824600006 }, "steps_from_proto": { "total": 1.930967347000228, "count": 2154, "is_parallel": true, "self": 0.20240524500037838, "children": { "_process_rank_one_or_two_observation": { "total": 1.7285621019998496, "count": 8616, "is_parallel": true, "self": 1.7285621019998496 } } } } } } } } } } }, "trainer_advance": { "total": 1.4155929949999475, "count": 1077, "self": 0.10694728299994871, "children": { "process_trajectory": { "total": 1.3086457119999988, "count": 1077, "self": 1.3086457119999988 } } } } }, "trainer_threads": { "total": 4.1599999889285755e-07, "count": 1, "self": 4.1599999889285755e-07 }, "TrainerController._save_models": { "total": 0.13269766699999508, "count": 1, "self": 0.0022704579999981434, "children": { "RLTrainer._checkpoint": { "total": 0.13042720899999694, "count": 1, "self": 0.13042720899999694 } } } } } } }