{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8506566882133484, "min": 0.8506566882133484, "max": 2.865962028503418, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8122.0703125, "min": 8122.0703125, "max": 29350.31640625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.175436019897461, "min": 0.2647911608219147, "max": 13.175436019897461, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2569.2099609375, "min": 51.369483947753906, "max": 2680.249267578125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06752742373960334, "min": 0.06170645971718591, "max": 0.0787032386721751, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27010969495841336, "min": 0.2477416956926212, "max": 0.3935161933608755, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21660422051654143, "min": 0.10558446428702012, "max": 0.29119298658242415, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8664168820661657, "min": 0.4223378571480805, "max": 1.400370804994714, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.5, "min": 2.9545454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 130.0, "max": 1426.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 2.9545454545454546, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 130.0, "max": 1426.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679835138", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679835618" }, "total": 479.765859097, "count": 1, "self": 0.7855446899999379, "children": { "run_training.setup": { "total": 0.10527234699998189, "count": 1, "self": 0.10527234699998189 }, "TrainerController.start_learning": { "total": 478.87504206000006, "count": 1, "self": 0.5786584889988262, "children": { "TrainerController._reset_env": { "total": 8.568912178999994, "count": 1, "self": 8.568912178999994 }, "TrainerController.advance": { "total": 469.4896163660012, "count": 18217, "self": 0.3002565040035279, "children": { "env_step": { "total": 469.1893598619977, "count": 18217, "self": 337.269975910001, "children": { "SubprocessEnvManager._take_step": { "total": 131.6321388540024, "count": 18217, "self": 2.585248975009108, "children": { "TorchPolicy.evaluate": { "total": 129.04688987899328, "count": 18217, "self": 129.04688987899328 } } }, "workers": { "total": 0.2872450979942869, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 477.1443186800003, "count": 18217, "is_parallel": true, "self": 231.9850377680067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005400000000008731, "count": 1, "is_parallel": true, "self": 0.003888253000241093, "children": { "_process_rank_one_or_two_observation": { "total": 0.001511746999767638, "count": 10, "is_parallel": true, "self": 0.001511746999767638 } } }, "UnityEnvironment.step": { "total": 0.06662894800001595, "count": 1, "is_parallel": true, "self": 0.0006013390001271546, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039723199995478353, "count": 1, "is_parallel": true, "self": 0.00039723199995478353 }, "communicator.exchange": { "total": 0.062248576000001776, "count": 1, "is_parallel": true, "self": 0.062248576000001776 }, "steps_from_proto": { "total": 0.0033818009999322385, "count": 1, "is_parallel": true, "self": 0.0004889939998520276, "children": { "_process_rank_one_or_two_observation": { "total": 0.002892807000080211, "count": 10, "is_parallel": true, "self": 0.002892807000080211 } } } } } } }, "UnityEnvironment.step": { "total": 245.15928091199362, "count": 18216, "is_parallel": true, "self": 9.791871377975212, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4189749760068935, "count": 18216, "is_parallel": true, "self": 5.4189749760068935 }, "communicator.exchange": { "total": 197.35461164201274, "count": 18216, "is_parallel": true, "self": 197.35461164201274 }, "steps_from_proto": { "total": 32.59382291599877, "count": 18216, "is_parallel": true, "self": 6.516924127991274, "children": { "_process_rank_one_or_two_observation": { "total": 26.076898788007497, "count": 182160, "is_parallel": true, "self": 26.076898788007497 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001529429999891363, "count": 1, "self": 0.0001529429999891363, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.86013529397644, "count": 419590, "is_parallel": true, "self": 10.694314912947561, "children": { "process_trajectory": { "total": 259.529073410029, "count": 419590, "is_parallel": true, "self": 258.33419024502905, "children": { "RLTrainer._checkpoint": { "total": 1.1948831649999647, "count": 4, "is_parallel": true, "self": 1.1948831649999647 } } }, "_update_policy": { "total": 195.63674697099987, "count": 90, "is_parallel": true, "self": 71.70064264000041, "children": { "TorchPPOOptimizer.update": { "total": 123.93610433099946, "count": 4587, "is_parallel": true, "self": 123.93610433099946 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2377020830000447, "count": 1, "self": 0.0012235200000532132, "children": { "RLTrainer._checkpoint": { "total": 0.23647856299999148, "count": 1, "self": 0.23647856299999148 } } } } } } }