{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.10233607888221741, "min": 0.09561286866664886, "max": 0.10375089943408966, "count": 750 }, "SoccerTwos.Policy.Entropy.sum": { "value": 20247.806640625, "min": 15746.4501953125, "max": 21757.6875, "count": 750 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.06762589928057, "min": 57.879858657243815, "max": 79.00638977635782, "count": 750 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 197568.0, "min": 148404.0, "max": 198416.0, "count": 750 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1821.3818951930884, "min": 1780.6596182123062, "max": 1847.0839211687107, "count": 750 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2531720.834318393, "min": 2089319.3899711026, "max": 3094186.6319391946, "count": 750 }, "SoccerTwos.Step.mean": { "value": 1419299994.0, "min": 1344399946.0, "max": 1419299994.0, "count": 750 }, "SoccerTwos.Step.sum": { "value": 1419299994.0, "min": 1344399946.0, "max": 1419299994.0, "count": 750 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.045758023858070374, "min": -0.053660083562135696, "max": 0.02153986319899559, "count": 750 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -63.46637725830078, "min": -72.17964172363281, "max": 30.06964874267578, "count": 750 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04583943262696266, "min": -0.05380823835730553, "max": 0.02180018648505211, "count": 750 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -63.57929229736328, "min": -72.81593322753906, "max": 30.433059692382812, "count": 750 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 750 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 750 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11655717404866786, "min": -0.1392843682282704, "max": 0.06828025104857538, "count": 750 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -161.66480040550232, "min": -187.51100021600723, "max": 87.12560033798218, "count": 750 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11655717404866786, "min": -0.1392843682282704, "max": 0.06828025104857538, "count": 750 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -161.66480040550232, "min": -187.51100021600723, "max": 87.12560033798218, "count": 750 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01518311547464691, "min": 0.013861440093217728, "max": 0.020582069853359523, "count": 750 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.07591557737323455, "min": 0.04990420994029894, "max": 0.10091212898259982, "count": 750 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0673966506868601, "min": 0.06056221661468347, "max": 0.07692732910315196, "count": 750 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.33698325343430047, "min": 0.22118995562195778, "max": 0.3846366455157598, "count": 750 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06770191306869187, "min": 0.06073326791326206, "max": 0.0772177549203237, "count": 750 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.3385095653434594, "min": 0.2222117992738883, "max": 0.3860887746016185, "count": 750 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 3.30293304500824e-05, "min": 3.30293304500824e-05, "max": 4.183935123722667e-05, "count": 750 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00016514665225041201, "min": 0.00012551805371168001, "max": 0.00020914805754381602, "count": 750 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 750 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 1.25, "min": 0.75, "max": 1.25, "count": 750 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0016598108858870589, "min": 0.0016598108858870589, "max": 0.0020998716442352946, "count": 750 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.008299054429435295, "min": 0.006299614932705884, "max": 0.010496925722776471, "count": 750 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 750 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 750 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679962205", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/home/jonatan/PycharmProjects/HuggingFaceDLUnit7/venv3.9/bin/mlagents-learn ./config/poca/0046.yaml --env=ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=0046 --num-envs=4 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.0+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1680009089" }, "total": 46883.23300168801, "count": 1, "self": 0.09526933800225379, "children": { "run_training.setup": { "total": 0.016086918003566097, "count": 1, "self": 0.016086918003566097 }, "TrainerController.start_learning": { "total": 46883.121645432, "count": 1, "self": 66.97268279066338, "children": { "TrainerController._reset_env": { "total": 18.318764213130635, "count": 377, "self": 18.318764213130635 }, "TrainerController.advance": { "total": 46797.703226105215, "count": 3614796, "self": 61.333452509352355, "children": { "env_step": { "total": 25654.539305632767, "count": 3614796, "self": 8752.083913006434, "children": { "SubprocessEnvManager._take_step": { "total": 16860.09403072307, "count": 5212483, "self": 427.6753272973001, "children": { "TorchPolicy.evaluate": { "total": 16432.41870342577, "count": 9568830, "self": 16432.41870342577 } } }, "workers": { "total": 42.36136190326215, "count": 3614796, "self": 0.0, "children": { "worker_root": { "total": 187346.76880229817, "count": 5211686, "is_parallel": true, "self": 131046.23209319863, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017411239969078451, "count": 2, "is_parallel": true, "self": 0.0003604459998314269, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013806779970764183, "count": 8, "is_parallel": true, "self": 0.0013806779970764183 } } }, "UnityEnvironment.step": { "total": 0.021498658999917097, "count": 1, "is_parallel": true, "self": 0.0007727450065431185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036098399868933484, "count": 1, "is_parallel": true, "self": 0.00036098399868933484 }, "communicator.exchange": { "total": 0.01841045799665153, "count": 1, "is_parallel": true, "self": 0.01841045799665153 }, "steps_from_proto": { "total": 0.0019544719980331138, "count": 2, "is_parallel": true, "self": 0.0003710620148922317, "children": { "_process_rank_one_or_two_observation": { "total": 0.001583409983140882, "count": 8, "is_parallel": true, "self": 0.001583409983140882 } } } } } } }, "steps_from_proto": { "total": 3.387118107857532, "count": 3008, "is_parallel": true, "self": 0.5347456304298248, "children": { "_process_rank_one_or_two_observation": { "total": 2.852372477427707, "count": 12032, "is_parallel": true, "self": 2.852372477427707 } } }, "UnityEnvironment.step": { "total": 56297.14959099168, "count": 5211685, "is_parallel": true, "self": 4073.1137725320077, "children": { "UnityEnvironment._generate_step_input": { "total": 2445.1282850332063, "count": 5211685, "is_parallel": true, "self": 2445.1282850332063 }, "communicator.exchange": { "total": 39569.729819547545, "count": 5211685, "is_parallel": true, "self": 39569.729819547545 }, "steps_from_proto": { "total": 10209.177713878918, "count": 10423370, "is_parallel": true, "self": 1728.1586247154992, "children": { "_process_rank_one_or_two_observation": { "total": 8481.01908916342, "count": 41693480, "is_parallel": true, "self": 8481.01908916342 } } } } } } } } } } }, "trainer_advance": { "total": 21081.830467963096, "count": 3614795, "self": 632.0771532913568, "children": { "process_trajectory": { "total": 9045.921679658852, "count": 3614795, "self": 9041.109260354846, "children": { "RLTrainer._checkpoint": { "total": 4.8124193040057435, "count": 37, "self": 4.8124193040057435 } } }, "_update_policy": { "total": 11403.831635012888, "count": 3641, "self": 8149.92792840601, "children": { "TorchPOCAOptimizer.update": { "total": 3253.9037066068777, "count": 109230, "self": 3253.9037066068777 } } } } } } }, "trainer_threads": { "total": 9.019859135150909e-07, "count": 1, "self": 9.019859135150909e-07 }, "TrainerController._save_models": { "total": 0.1269714210066013, "count": 1, "self": 0.0022791520023019984, "children": { "RLTrainer._checkpoint": { "total": 0.1246922690042993, "count": 1, "self": 0.1246922690042993 } } } } } } }