{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.927580714225769, "min": 0.9160346388816833, "max": 2.855306386947632, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8897.3544921875, "min": 8791.5126953125, "max": 29782.46875, "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": 12.933603286743164, "min": 0.4558081030845642, "max": 12.933603286743164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1306.2939453125, "min": 44.21338653564453, "max": 1306.2939453125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.173076923076923, "min": 3.159090909090909, "max": 26.173076923076923, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1361.0, "min": 139.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.173076923076923, "min": 3.159090909090909, "max": 26.173076923076923, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1361.0, "min": 139.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0684924630965243, "min": 0.06140695525031975, "max": 0.07392471188273596, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2739698523860972, "min": 0.2580428900329542, "max": 0.3613633234818539, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21627024488121854, "min": 0.113190196454525, "max": 0.30498550057995555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8650809795248742, "min": 0.4527607858181, "max": 1.4992423887346304, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.950097350000008e-06, "min": 7.950097350000008e-06, "max": 0.00029175000274999995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.180038940000003e-05, "min": 3.180038940000003e-05, "max": 0.0013845000385, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10265, "min": 0.10265, "max": 0.19725000000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4106, "min": 0.4106, "max": 0.9615, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014223500000000013, "min": 0.00014223500000000013, "max": 0.004862775, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005689400000000005, "min": 0.0005689400000000005, "max": 0.023078849999999998, "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": "1673447438", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673447858" }, "total": 420.19481529100005, "count": 1, "self": 0.4365156979998801, "children": { "run_training.setup": { "total": 0.10711761100003514, "count": 1, "self": 0.10711761100003514 }, "TrainerController.start_learning": { "total": 419.65118198200014, "count": 1, "self": 0.5547065320167803, "children": { "TrainerController._reset_env": { "total": 7.215333659999942, "count": 1, "self": 7.215333659999942 }, "TrainerController.advance": { "total": 411.7628916309835, "count": 18207, "self": 0.2642775769875243, "children": { "env_step": { "total": 411.498614053996, "count": 18207, "self": 257.4721888349982, "children": { "SubprocessEnvManager._take_step": { "total": 153.7431350309895, "count": 18207, "self": 1.4291393679728799, "children": { "TorchPolicy.evaluate": { "total": 152.3139956630166, "count": 18207, "self": 34.30641705903213, "children": { "TorchPolicy.sample_actions": { "total": 118.00757860398448, "count": 18207, "self": 118.00757860398448 } } } } }, "workers": { "total": 0.28329018800832273, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 418.3196818200049, "count": 18207, "is_parallel": true, "self": 200.1473207470125, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006308831999945141, "count": 1, "is_parallel": true, "self": 0.0036583830000154194, "children": { "_process_rank_one_or_two_observation": { "total": 0.002650448999929722, "count": 10, "is_parallel": true, "self": 0.002650448999929722 } } }, "UnityEnvironment.step": { "total": 0.05599797299998954, "count": 1, "is_parallel": true, "self": 0.0005315219998465182, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002856220000921894, "count": 1, "is_parallel": true, "self": 0.0002856220000921894 }, "communicator.exchange": { "total": 0.053360326000074565, "count": 1, "is_parallel": true, "self": 0.053360326000074565 }, "steps_from_proto": { "total": 0.00182050299997627, "count": 1, "is_parallel": true, "self": 0.00042096200002106343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013995409999552066, "count": 10, "is_parallel": true, "self": 0.0013995409999552066 } } } } } } }, "UnityEnvironment.step": { "total": 218.17236107299243, "count": 18206, "is_parallel": true, "self": 8.42246086101784, "children": { "UnityEnvironment._generate_step_input": { "total": 4.8696969809936945, "count": 18206, "is_parallel": true, "self": 4.8696969809936945 }, "communicator.exchange": { "total": 174.83643765299985, "count": 18206, "is_parallel": true, "self": 174.83643765299985 }, "steps_from_proto": { "total": 30.04376557798105, "count": 18206, "is_parallel": true, "self": 6.569092834001822, "children": { "_process_rank_one_or_two_observation": { "total": 23.474672743979227, "count": 182060, "is_parallel": true, "self": 23.474672743979227 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.549300001599477e-05, "count": 1, "self": 4.549300001599477e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 409.53406234994236, "count": 281808, "is_parallel": true, "self": 7.372327747974964, "children": { "process_trajectory": { "total": 194.9891688759675, "count": 281808, "is_parallel": true, "self": 193.1086466129674, "children": { "RLTrainer._checkpoint": { "total": 1.8805222630001026, "count": 10, "is_parallel": true, "self": 1.8805222630001026 } } }, "_update_policy": { "total": 207.1725657259999, "count": 90, "is_parallel": true, "self": 45.59986695699763, "children": { "TorchPPOOptimizer.update": { "total": 161.57269876900227, "count": 4590, "is_parallel": true, "self": 161.57269876900227 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11820466599988322, "count": 1, "self": 0.0011067659997934243, "children": { "RLTrainer._checkpoint": { "total": 0.1170979000000898, "count": 1, "self": 0.1170979000000898 } } } } } } }