{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7749292254447937, "min": 0.7701823115348816, "max": 2.8747100830078125, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7944.57421875, "min": 7551.8603515625, "max": 29439.90625, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.387446403503418, "min": 0.3494293689727783, "max": 13.387446403503418, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2731.0390625, "min": 67.78929901123047, "max": 2734.8154296875, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06889049390173407, "min": 0.05944812488456841, "max": 0.07449358001661797, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34445246950867037, "min": 0.24058301910704089, "max": 0.3724679000830899, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21044053075944674, "min": 0.11564480345559251, "max": 0.2917678328705769, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0522026537972338, "min": 0.46257921382237005, "max": 1.4588391643528844, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333331e-06, "min": 5.288098237333331e-06, "max": 0.00029458800180399996, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.6440491186666655e-05, "min": 2.6440491186666655e-05, "max": 0.0014234400255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.272727272727273, "min": 2.9318181818181817, "max": 26.34090909090909, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1445.0, "min": 129.0, "max": 1445.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 2.9318181818181817, "max": 26.34090909090909, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1445.0, "min": 129.0, "max": 1445.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692625998", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692626706" }, "total": 708.0994092830001, "count": 1, "self": 0.4739599630001976, "children": { "run_training.setup": { "total": 0.0387123860000429, "count": 1, "self": 0.0387123860000429 }, "TrainerController.start_learning": { "total": 707.5867369339999, "count": 1, "self": 0.8243218230102229, "children": { "TrainerController._reset_env": { "total": 4.828966600000058, "count": 1, "self": 4.828966600000058 }, "TrainerController.advance": { "total": 701.7841805649894, "count": 27335, "self": 0.40119524400302, "children": { "env_step": { "total": 701.3829853209863, "count": 27335, "self": 510.08902676098614, "children": { "SubprocessEnvManager._take_step": { "total": 190.88228486496564, "count": 27335, "self": 2.573468849956498, "children": { "TorchPolicy.evaluate": { "total": 188.30881601500914, "count": 27335, "self": 188.30881601500914 } } }, "workers": { "total": 0.4116736950345512, "count": 27335, "self": 0.0, "children": { "worker_root": { "total": 705.2690534840037, "count": 27335, "is_parallel": true, "self": 333.06623742704005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019976010000846145, "count": 1, "is_parallel": true, "self": 0.000562833000003593, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014347680000810215, "count": 10, "is_parallel": true, "self": 0.0014347680000810215 } } }, "UnityEnvironment.step": { "total": 0.09415475099990545, "count": 1, "is_parallel": true, "self": 0.0006249639998259227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041969700009758526, "count": 1, "is_parallel": true, "self": 0.00041969700009758526 }, "communicator.exchange": { "total": 0.0888378439999542, "count": 1, "is_parallel": true, "self": 0.0888378439999542 }, "steps_from_proto": { "total": 0.004272246000027735, "count": 1, "is_parallel": true, "self": 0.0005533369999284332, "children": { "_process_rank_one_or_two_observation": { "total": 0.003718909000099302, "count": 10, "is_parallel": true, "self": 0.003718909000099302 } } } } } } }, "UnityEnvironment.step": { "total": 372.2028160569637, "count": 27334, "is_parallel": true, "self": 15.74251820698828, "children": { "UnityEnvironment._generate_step_input": { "total": 7.890380504023142, "count": 27334, "is_parallel": true, "self": 7.890380504023142 }, "communicator.exchange": { "total": 294.3105855889587, "count": 27334, "is_parallel": true, "self": 294.3105855889587 }, "steps_from_proto": { "total": 54.25933175699356, "count": 27334, "is_parallel": true, "self": 9.876486163057052, "children": { "_process_rank_one_or_two_observation": { "total": 44.38284559393651, "count": 273340, "is_parallel": true, "self": 44.38284559393651 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00046047100022406084, "count": 1, "self": 0.00046047100022406084, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 696.4251378809527, "count": 667804, "is_parallel": true, "self": 14.456156370762073, "children": { "process_trajectory": { "total": 378.2406189941878, "count": 667804, "is_parallel": true, "self": 376.268529299188, "children": { "RLTrainer._checkpoint": { "total": 1.972089694999795, "count": 6, "is_parallel": true, "self": 1.972089694999795 } } }, "_update_policy": { "total": 303.7283625160028, "count": 136, "is_parallel": true, "self": 122.27675173402031, "children": { "TorchPPOOptimizer.update": { "total": 181.45161078198248, "count": 6933, "is_parallel": true, "self": 181.45161078198248 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14880747500001235, "count": 1, "self": 0.0008799679999356158, "children": { "RLTrainer._checkpoint": { "total": 0.14792750700007673, "count": 1, "self": 0.14792750700007673 } } } } } } }