{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2956435680389404, "min": 3.2956435680389404, "max": 3.2956435680389404, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105460.59375, "min": 105460.59375, "max": 105460.59375, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 689.7, "min": 689.7, "max": 689.7, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 27588.0, "min": 27588.0, "max": 27588.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.5733196942704, "min": 1197.5733196942704, "max": 1197.5733196942704, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11975.733196942703, "min": 11975.733196942703, "max": 11975.733196942703, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9814.0, "min": 9814.0, "max": 9814.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9814.0, "min": 9814.0, "max": 9814.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.049709100276231766, "min": -0.049709100276231766, "max": -0.049709100276231766, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7953456044197083, "min": -0.7953456044197083, "max": -0.7953456044197083, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.049606382846832275, "min": -0.049606382846832275, "max": -0.049606382846832275, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7937021255493164, "min": -0.7937021255493164, "max": -0.7937021255493164, "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": -0.407150000333786, "min": -0.407150000333786, "max": -0.407150000333786, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.514400005340576, "min": -6.514400005340576, "max": -6.514400005340576, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.407150000333786, "min": -0.407150000333786, "max": -0.407150000333786, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.514400005340576, "min": -6.514400005340576, "max": -6.514400005340576, "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": "1713753819", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/conlanrios/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1713753957" }, "total": 138.0961150819203, "count": 1, "self": 0.29653055081143975, "children": { "run_training.setup": { "total": 0.04165997006930411, "count": 1, "self": 0.04165997006930411 }, "TrainerController.start_learning": { "total": 137.75792456103954, "count": 1, "self": 0.028438515961170197, "children": { "TrainerController._reset_env": { "total": 6.768105186987668, "count": 1, "self": 6.768105186987668 }, "TrainerController.advance": { "total": 130.73639970924705, "count": 1157, "self": 0.02896854595746845, "children": { "env_step": { "total": 128.1499001227785, "count": 1157, "self": 123.84522933594417, "children": { "SubprocessEnvManager._take_step": { "total": 4.286475580185652, "count": 1157, "self": 0.16512485139537603, "children": { "TorchPolicy.evaluate": { "total": 4.121350728790276, "count": 2308, "self": 4.121350728790276 } } }, "workers": { "total": 0.018195206648670137, "count": 1156, "self": 0.0, "children": { "worker_root": { "total": 132.20726126793306, "count": 1156, "is_parallel": true, "self": 11.972756742383353, "children": { "steps_from_proto": { "total": 0.004312571021728218, "count": 2, "is_parallel": true, "self": 0.0007999339140951633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0035126371076330543, "count": 8, "is_parallel": true, "self": 0.0035126371076330543 } } }, "UnityEnvironment.step": { "total": 120.23019195452798, "count": 1156, "is_parallel": true, "self": 0.35049448150675744, "children": { "UnityEnvironment._generate_step_input": { "total": 2.366147710941732, "count": 1156, "is_parallel": true, "self": 2.366147710941732 }, "communicator.exchange": { "total": 113.23947233846411, "count": 1156, "is_parallel": true, "self": 113.23947233846411 }, "steps_from_proto": { "total": 4.274077423615381, "count": 2312, "is_parallel": true, "self": 0.6028466142015532, "children": { "_process_rank_one_or_two_observation": { "total": 3.671230809413828, "count": 9248, "is_parallel": true, "self": 3.671230809413828 } } } } } } } } } } }, "trainer_advance": { "total": 2.557531040511094, "count": 1156, "self": 0.11648016411345452, "children": { "process_trajectory": { "total": 2.4410508763976395, "count": 1156, "self": 2.4410508763976395 } } } } }, "trainer_threads": { "total": 1.483946107327938e-06, "count": 1, "self": 1.483946107327938e-06 }, "TrainerController._save_models": { "total": 0.22497966489754617, "count": 1, "self": 0.0014202659949660301, "children": { "RLTrainer._checkpoint": { "total": 0.22355939890258014, "count": 1, "self": 0.22355939890258014 } } } } } } }