{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9587792754173279, "min": 0.9587792754173279, "max": 2.866180419921875, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9154.4248046875, "min": 9154.4248046875, "max": 29384.08203125, "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": 12.483307838439941, "min": 0.3554987907409668, "max": 12.483307838439941, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2434.2451171875, "min": 68.96676635742188, "max": 2523.12060546875, "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": 0.061833701907280735, "min": 0.061833701907280735, "max": 0.07801945624831955, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24733480762912294, "min": 0.24733480762912294, "max": 0.3900972812415977, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23269071839019365, "min": 0.13106635059503946, "max": 0.3082172705846674, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9307628735607746, "min": 0.5242654023801578, "max": 1.5410863529233372, "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": 24.886363636363637, "min": 3.659090909090909, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 161.0, "max": 1346.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 3.659090909090909, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 161.0, "max": 1346.0, "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": "1681325548", "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": "1681326015" }, "total": 466.69733981699994, "count": 1, "self": 0.3861508799999456, "children": { "run_training.setup": { "total": 0.19596021799998198, "count": 1, "self": 0.19596021799998198 }, "TrainerController.start_learning": { "total": 466.115228719, "count": 1, "self": 0.5549021340021909, "children": { "TrainerController._reset_env": { "total": 4.435136858999954, "count": 1, "self": 4.435136858999954 }, "TrainerController.advance": { "total": 460.9929625649977, "count": 18202, "self": 0.27043280199552555, "children": { "env_step": { "total": 460.72252976300217, "count": 18202, "self": 335.8267926240072, "children": { "SubprocessEnvManager._take_step": { "total": 124.62297852699885, "count": 18202, "self": 1.9198823849947075, "children": { "TorchPolicy.evaluate": { "total": 122.70309614200414, "count": 18202, "self": 122.70309614200414 } } }, "workers": { "total": 0.2727586119960961, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 464.59817497501047, "count": 18202, "is_parallel": true, "self": 215.93620333899526, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006127264000042487, "count": 1, "is_parallel": true, "self": 0.0038261970003077295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023010669997347577, "count": 10, "is_parallel": true, "self": 0.0023010669997347577 } } }, "UnityEnvironment.step": { "total": 0.03959327199993368, "count": 1, "is_parallel": true, "self": 0.0006350879999672543, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040306300002157514, "count": 1, "is_parallel": true, "self": 0.00040306300002157514 }, "communicator.exchange": { "total": 0.036216600999978255, "count": 1, "is_parallel": true, "self": 0.036216600999978255 }, "steps_from_proto": { "total": 0.002338519999966593, "count": 1, "is_parallel": true, "self": 0.00046619499971711775, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018723250002494751, "count": 10, "is_parallel": true, "self": 0.0018723250002494751 } } } } } } }, "UnityEnvironment.step": { "total": 248.6619716360152, "count": 18201, "is_parallel": true, "self": 9.890332982005134, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6089358080014335, "count": 18201, "is_parallel": true, "self": 5.6089358080014335 }, "communicator.exchange": { "total": 200.01929402600365, "count": 18201, "is_parallel": true, "self": 200.01929402600365 }, "steps_from_proto": { "total": 33.14340882000499, "count": 18201, "is_parallel": true, "self": 6.532137901992542, "children": { "_process_rank_one_or_two_observation": { "total": 26.61127091801245, "count": 182010, "is_parallel": true, "self": 26.61127091801245 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012049300016769848, "count": 1, "self": 0.00012049300016769848, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.4796484979437, "count": 405411, "is_parallel": true, "self": 9.875323571995978, "children": { "process_trajectory": { "total": 251.7430120089473, "count": 405411, "is_parallel": true, "self": 250.51229163994697, "children": { "RLTrainer._checkpoint": { "total": 1.2307203690003234, "count": 4, "is_parallel": true, "self": 1.2307203690003234 } } }, "_update_policy": { "total": 195.86131291700042, "count": 90, "is_parallel": true, "self": 74.58981016299686, "children": { "TorchPPOOptimizer.update": { "total": 121.27150275400356, "count": 4584, "is_parallel": true, "self": 121.27150275400356 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1321066680000058, "count": 1, "self": 0.0008952569999109983, "children": { "RLTrainer._checkpoint": { "total": 0.1312114110000948, "count": 1, "self": 0.1312114110000948 } } } } } } }