{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7874191999435425, "min": 1.6476508378982544, "max": 3.2957353591918945, "count": 1013 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35748.3828125, "min": 21115.220703125, "max": 105463.53125, "count": 1013 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.36448598130841, "min": 39.83606557377049, "max": 999.0, "count": 1013 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19416.0, "min": 14248.0, "max": 28800.0, "count": 1013 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1811.1505143977136, "min": 1196.5444678740403, "max": 1811.1505143977136, "count": 1002 }, "SoccerTwos.Self-play.ELO.sum": { "value": 387586.2100811107, "min": 2394.111747409965, "max": 438681.0905175323, "count": 1002 }, "SoccerTwos.Step.mean": { "value": 10129976.0, "min": 9418.0, "max": 10129976.0, "count": 1013 }, "SoccerTwos.Step.sum": { "value": 10129976.0, "min": 9418.0, "max": 10129976.0, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01859966851770878, "min": -0.12144982069730759, "max": 0.37329086661338806, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.9803290367126465, "min": -23.087608337402344, "max": 63.21400833129883, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0250899326056242, "min": -0.12162947654724121, "max": 0.3714117109775543, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.369245529174805, "min": -23.222564697265625, "max": 64.84752655029297, "count": 1013 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1013 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1243850477387972, "min": -0.42857142857142855, "max": 0.7399550403735434, "count": 1013 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 26.6184002161026, "min": -67.58319973945618, "max": 104.66119998693466, "count": 1013 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1243850477387972, "min": -0.42857142857142855, "max": 0.7399550403735434, "count": 1013 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 26.6184002161026, "min": -67.58319973945618, "max": 104.66119998693466, "count": 1013 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1013 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1013 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017043348409545918, "min": 0.010409917752410063, "max": 0.024958913982845842, "count": 489 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017043348409545918, "min": 0.010409917752410063, "max": 0.024958913982845842, "count": 489 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.13683981994787853, "min": 1.4902243462226276e-05, "max": 0.1441478818655014, "count": 489 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.13683981994787853, "min": 1.4902243462226276e-05, "max": 0.1441478818655014, "count": 489 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.13990804354349773, "min": 1.5946089479257353e-05, "max": 0.1476387416323026, "count": 489 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.13990804354349773, "min": 1.5946089479257353e-05, "max": 0.1476387416323026, "count": 489 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 489 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 489 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 489 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 489 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 489 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 489 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704822592", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/iansotnek/miniconda3/envs/HR_RL/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2", "numpy_version": "1.23.5", "end_time_seconds": "1704862218" }, "total": 39625.545456541935, "count": 1, "self": 0.1374219588469714, "children": { "run_training.setup": { "total": 0.02558012504596263, "count": 1, "self": 0.02558012504596263 }, "TrainerController.start_learning": { "total": 39625.38245445804, "count": 1, "self": 9.146190472063608, "children": { "TrainerController._reset_env": { "total": 3.736145206959918, "count": 21, "self": 3.736145206959918 }, "TrainerController.advance": { "total": 39612.39079132001, "count": 694359, "self": 7.257875319686718, "children": { "env_step": { "total": 30897.004989898414, "count": 694359, "self": 29614.918273467687, "children": { "SubprocessEnvManager._take_step": { "total": 1276.7451207719278, "count": 694359, "self": 36.365398046094924, "children": { "TorchPolicy.evaluate": { "total": 1240.3797227258328, "count": 1270470, "self": 1240.3797227258328 } } }, "workers": { "total": 5.341595658799633, "count": 694358, "self": 0.0, "children": { "worker_root": { "total": 39609.311667990405, "count": 694358, "is_parallel": true, "self": 10964.771836633328, "children": { "steps_from_proto": { "total": 0.03269091481342912, "count": 42, "is_parallel": true, "self": 0.0038325353525578976, "children": { "_process_rank_one_or_two_observation": { "total": 0.02885837946087122, "count": 168, "is_parallel": true, "self": 0.02885837946087122 } } }, "UnityEnvironment.step": { "total": 28644.507140442263, "count": 694358, "is_parallel": true, "self": 88.72919556580018, "children": { "UnityEnvironment._generate_step_input": { "total": 531.4733891009819, "count": 694358, "is_parallel": true, "self": 531.4733891009819 }, "communicator.exchange": { "total": 26944.79102874978, "count": 694358, "is_parallel": true, "self": 26944.79102874978 }, "steps_from_proto": { "total": 1079.5135270257015, "count": 1388716, "is_parallel": true, "self": 121.61215638555586, "children": { "_process_rank_one_or_two_observation": { "total": 957.9013706401456, "count": 5554864, "is_parallel": true, "self": 957.9013706401456 } } } } } } } } } } }, "trainer_advance": { "total": 8708.127926101908, "count": 694358, "self": 65.48424990929198, "children": { "process_trajectory": { "total": 1728.411740395939, "count": 694358, "self": 1726.142939104, "children": { "RLTrainer._checkpoint": { "total": 2.268801291938871, "count": 20, "self": 2.268801291938871 } } }, "_update_policy": { "total": 6914.231935796677, "count": 489, "self": 675.4875539799687, "children": { "TorchPOCAOptimizer.update": { "total": 6238.7443818167085, "count": 14673, "self": 6238.7443818167085 } } } } } } }, "trainer_threads": { "total": 5.84055669605732e-07, "count": 1, "self": 5.84055669605732e-07 }, "TrainerController._save_models": { "total": 0.10932687495369464, "count": 1, "self": 0.0007386249490082264, "children": { "RLTrainer._checkpoint": { "total": 0.10858825000468642, "count": 1, "self": 0.10858825000468642 } } } } } } }