{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0124666690826416, "min": 2.9511051177978516, "max": 3.2957208156585693, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54947.390625, "min": 6622.83154296875, "max": 174162.09375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 459.8181818181818, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16256.0, "max": 25644.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1183.6499847128998, "min": 1172.1853616288624, "max": 1209.5404284835304, "count": 238 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2367.2999694257996, "min": 2344.624869395175, "max": 14487.913295373062, "count": 238 }, "SoccerTwos.Step.mean": { "value": 4999216.0, "min": 9840.0, "max": 4999216.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999216.0, "min": 9840.0, "max": 4999216.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0001419692998751998, "min": -0.042389705777168274, "max": 0.005097269546240568, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.001419692998751998, "min": -0.6358456015586853, "max": 0.06626450270414352, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0001376348955091089, "min": -0.04256816208362579, "max": 0.005087260622531176, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.00137634901329875, "min": -0.6385224461555481, "max": 0.06613438576459885, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.3442666620016098, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 5.163999930024147, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6153846153846154, "max": 0.3442666620016098, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 5.163999930024147, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01263563557974218, "min": 0.01085039165627677, "max": 0.023399240154928218, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01263563557974218, "min": 0.01085039165627677, "max": 0.023399240154928218, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.3229819284532596e-08, "min": 1.1274310729447734e-08, "max": 0.0050628191403423745, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.3229819284532596e-08, "min": 1.1274310729447734e-08, "max": 0.0050628191403423745, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.5037846079479777e-08, "min": 1.1883867904553351e-08, "max": 0.005072414642199874, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.5037846079479777e-08, "min": 1.1883867904553351e-08, "max": 0.005072414642199874, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726843038", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726851610" }, "total": 8572.478007618, "count": 1, "self": 0.27119378299903474, "children": { "run_training.setup": { "total": 0.017031851999945502, "count": 1, "self": 0.017031851999945502 }, "TrainerController.start_learning": { "total": 8572.189781983001, "count": 1, "self": 5.447468926608053, "children": { "TrainerController._reset_env": { "total": 5.7966749169927425, "count": 50, "self": 5.7966749169927425 }, "TrainerController.advance": { "total": 8560.8602641674, "count": 336595, "self": 5.809992708724167, "children": { "env_step": { "total": 7168.290361189549, "count": 336595, "self": 5127.917312758353, "children": { "SubprocessEnvManager._take_step": { "total": 2037.0394862400317, "count": 336595, "self": 42.82979268647205, "children": { "TorchPolicy.evaluate": { "total": 1994.2096935535596, "count": 668724, "self": 1994.2096935535596 } } }, "workers": { "total": 3.3335621911651288, "count": 336595, "self": 0.0, "children": { "worker_root": { "total": 8561.248702222374, "count": 336595, "is_parallel": true, "self": 4244.798898831312, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031370659999083728, "count": 2, "is_parallel": true, "self": 0.0008433429998149222, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022937230000934505, "count": 8, "is_parallel": true, "self": 0.0022937230000934505 } } }, "UnityEnvironment.step": { "total": 0.028315590000147495, "count": 1, "is_parallel": true, "self": 0.000572595999983605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004704620000666182, "count": 1, "is_parallel": true, "self": 0.0004704620000666182 }, "communicator.exchange": { "total": 0.025429956000152742, "count": 1, "is_parallel": true, "self": 0.025429956000152742 }, "steps_from_proto": { "total": 0.001842575999944529, "count": 2, "is_parallel": true, "self": 0.0003693639996527054, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014732120002918236, "count": 8, "is_parallel": true, "self": 0.0014732120002918236 } } } } } } }, "UnityEnvironment.step": { "total": 4316.354633424056, "count": 336594, "is_parallel": true, "self": 192.70362476589798, "children": { "UnityEnvironment._generate_step_input": { "total": 128.96691993589093, "count": 336594, "is_parallel": true, "self": 128.96691993589093 }, "communicator.exchange": { "total": 3389.900820071082, "count": 336594, "is_parallel": true, "self": 3389.900820071082 }, "steps_from_proto": { "total": 604.7832686511852, "count": 673188, "is_parallel": true, "self": 110.26707167057657, "children": { "_process_rank_one_or_two_observation": { "total": 494.5161969806086, "count": 2692752, "is_parallel": true, "self": 494.5161969806086 } } } } }, "steps_from_proto": { "total": 0.09516996700631353, "count": 98, "is_parallel": true, "self": 0.018052341998554766, "children": { "_process_rank_one_or_two_observation": { "total": 0.07711762500775876, "count": 392, "is_parallel": true, "self": 0.07711762500775876 } } } } } } } } }, "trainer_advance": { "total": 1386.759910269127, "count": 336595, "self": 46.33405343833556, "children": { "process_trajectory": { "total": 395.4562756127966, "count": 336595, "self": 394.5691358557956, "children": { "RLTrainer._checkpoint": { "total": 0.8871397570010231, "count": 10, "self": 0.8871397570010231 } } }, "_update_policy": { "total": 944.9695812179948, "count": 231, "self": 612.9957543329574, "children": { "TorchPOCAOptimizer.update": { "total": 331.9738268850374, "count": 6930, "self": 331.9738268850374 } } } } } } }, "trainer_threads": { "total": 1.128999429056421e-06, "count": 1, "self": 1.128999429056421e-06 }, "TrainerController._save_models": { "total": 0.08537284299927705, "count": 1, "self": 0.0008364460009033792, "children": { "RLTrainer._checkpoint": { "total": 0.08453639699837368, "count": 1, "self": 0.08453639699837368 } } } } } } }