{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.09933372586965561, "min": 0.09933372586965561, "max": 0.09933372586965561, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 3537.869873046875, "min": 3537.869873046875, "max": 3537.869873046875, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.83620689655172, "min": 60.83620689655172, "max": 60.83620689655172, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 28228.0, "min": 28228.0, "max": 28228.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.3202206521769, "min": 1198.3202206521769, "max": 1198.3202206521769, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278010.29119130503, "min": 278010.29119130503, "max": 278010.29119130503, "count": 1 }, "SoccerTwos.Step.mean": { "value": 1419399900.0, "min": 1419399900.0, "max": 1419399900.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 1419399900.0, "min": 1419399900.0, "max": 1419399900.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.026738332584500313, "min": -0.026738332584500313, "max": -0.026738332584500313, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.1765546798706055, "min": -6.1765546798706055, "max": -6.1765546798706055, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026743851602077484, "min": -0.026743851602077484, "max": -0.026743851602077484, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.177829742431641, "min": -6.177829742431641, "max": -6.177829742431641, "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": 0.0029281393274084313, "min": 0.0029281393274084313, "max": 0.0029281393274084313, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.6764001846313477, "min": 0.6764001846313477, "max": 0.6764001846313477, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0029281393274084313, "min": 0.0029281393274084313, "max": 0.0029281393274084313, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.6764001846313477, "min": 0.6764001846313477, "max": 0.6764001846313477, "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": "1709787753", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/RL/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709787788" }, "total": 35.066706048000015, "count": 1, "self": 0.025682736999442568, "children": { "run_training.setup": { "total": 0.043086405000394734, "count": 1, "self": 0.043086405000394734 }, "TrainerController.start_learning": { "total": 34.99793690600018, "count": 1, "self": 0.03311267800290807, "children": { "TrainerController._reset_env": { "total": 2.553982784999789, "count": 2, "self": 2.553982784999789 }, "TrainerController.advance": { "total": 32.21173693199671, "count": 929, "self": 0.028066299975762377, "children": { "env_step": { "total": 20.060912058016584, "count": 929, "self": 9.68049199800953, "children": { "SubprocessEnvManager._take_step": { "total": 10.349823087002733, "count": 1670, "self": 0.25925154302240117, "children": { "TorchPolicy.evaluate": { "total": 10.090571543980332, "count": 3088, "self": 10.090571543980332 } } }, "workers": { "total": 0.030596973004321626, "count": 929, "self": 0.0, "children": { "worker_root": { "total": 114.9102212120124, "count": 1664, "is_parallel": true, "self": 77.16485679001653, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034152719999838155, "count": 2, "is_parallel": true, "self": 0.0007510000014008256, "children": { "_process_rank_one_or_two_observation": { "total": 0.00266427199858299, "count": 8, "is_parallel": true, "self": 0.00266427199858299 } } }, "UnityEnvironment.step": { "total": 0.05908933199953026, "count": 1, "is_parallel": true, "self": 0.0008054329991864506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005577410001933458, "count": 1, "is_parallel": true, "self": 0.0005577410001933458 }, "communicator.exchange": { "total": 0.05536173700056679, "count": 1, "is_parallel": true, "self": 0.05536173700056679 }, "steps_from_proto": { "total": 0.002364420999583672, "count": 2, "is_parallel": true, "self": 0.00042512099753366783, "children": { "_process_rank_one_or_two_observation": { "total": 0.001939300002050004, "count": 8, "is_parallel": true, "self": 0.001939300002050004 } } } } } } }, "steps_from_proto": { "total": 0.010176472999773978, "count": 8, "is_parallel": true, "self": 0.001472500002819288, "children": { "_process_rank_one_or_two_observation": { "total": 0.00870397299695469, "count": 32, "is_parallel": true, "self": 0.00870397299695469 } } }, "UnityEnvironment.step": { "total": 37.7351879489961, "count": 1663, "is_parallel": true, "self": 1.565610092992756, "children": { "UnityEnvironment._generate_step_input": { "total": 1.0208460379935786, "count": 1663, "is_parallel": true, "self": 1.0208460379935786 }, "communicator.exchange": { "total": 29.520980537976357, "count": 1663, "is_parallel": true, "self": 29.520980537976357 }, "steps_from_proto": { "total": 5.627751280033408, "count": 3326, "is_parallel": true, "self": 1.1510016900292612, "children": { "_process_rank_one_or_two_observation": { "total": 4.476749590004147, "count": 13304, "is_parallel": true, "self": 4.476749590004147 } } } } } } } } } } }, "trainer_advance": { "total": 12.122758574004365, "count": 929, "self": 0.3003509300069709, "children": { "process_trajectory": { "total": 7.963413221998053, "count": 929, "self": 7.963413221998053 }, "_update_policy": { "total": 3.8589944219993413, "count": 1, "self": 0.7988670859986087, "children": { "TorchPOCAOptimizer.update": { "total": 3.0601273360007326, "count": 2, "self": 3.0601273360007326 } } } } } } }, "trainer_threads": { "total": 1.5020004866528325e-06, "count": 1, "self": 1.5020004866528325e-06 }, "TrainerController._save_models": { "total": 0.19910300900028233, "count": 1, "self": 0.006135685001027014, "children": { "RLTrainer._checkpoint": { "total": 0.1929673239992553, "count": 1, "self": 0.1929673239992553 } } } } } } }