{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.109220027923584, "min": 1.109220027923584, "max": 2.874509572982788, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10651.83984375, "min": 10651.83984375, "max": 29437.853515625, "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": 12.509050369262695, "min": 0.4433053135871887, "max": 12.509050369262695, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2439.264892578125, "min": 86.00122833251953, "max": 2506.47802734375, "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.Losses.PolicyLoss.mean": { "value": 0.06941677913881208, "min": 0.06268367462325841, "max": 0.07420617734754285, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27766711655524834, "min": 0.25073469849303365, "max": 0.35476253323002876, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20649302524386667, "min": 0.11540351335333623, "max": 0.2885289260569741, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8259721009754667, "min": 0.46161405341334494, "max": 1.4426446302848706, "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": 25.25, "min": 3.25, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 143.0, "max": 1349.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.25, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 143.0, "max": 1349.0, "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": "1680722766", "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": "1680723225" }, "total": 459.53633219899996, "count": 1, "self": 0.8385480459998575, "children": { "run_training.setup": { "total": 0.10955127800002629, "count": 1, "self": 0.10955127800002629 }, "TrainerController.start_learning": { "total": 458.5882328750001, "count": 1, "self": 0.5549748029926604, "children": { "TrainerController._reset_env": { "total": 3.930294607999997, "count": 1, "self": 3.930294607999997 }, "TrainerController.advance": { "total": 453.88803937800753, "count": 18222, "self": 0.27552384599874813, "children": { "env_step": { "total": 453.6125155320088, "count": 18222, "self": 334.7367689289958, "children": { "SubprocessEnvManager._take_step": { "total": 118.60141212600422, "count": 18222, "self": 1.6478542400009815, "children": { "TorchPolicy.evaluate": { "total": 116.95355788600324, "count": 18222, "self": 116.95355788600324 } } }, "workers": { "total": 0.2743344770087788, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 457.00839258499406, "count": 18222, "is_parallel": true, "self": 210.83706595399235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004812962000016796, "count": 1, "is_parallel": true, "self": 0.0031248619999360017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016881000000807944, "count": 10, "is_parallel": true, "self": 0.0016881000000807944 } } }, "UnityEnvironment.step": { "total": 0.036083200999996734, "count": 1, "is_parallel": true, "self": 0.0006216170000357124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000414060000025529, "count": 1, "is_parallel": true, "self": 0.000414060000025529 }, "communicator.exchange": { "total": 0.033221355999955904, "count": 1, "is_parallel": true, "self": 0.033221355999955904 }, "steps_from_proto": { "total": 0.0018261679999795888, "count": 1, "is_parallel": true, "self": 0.00037380800000619274, "children": { "_process_rank_one_or_two_observation": { "total": 0.001452359999973396, "count": 10, "is_parallel": true, "self": 0.001452359999973396 } } } } } } }, "UnityEnvironment.step": { "total": 246.1713266310017, "count": 18221, "is_parallel": true, "self": 9.943378263996578, "children": { "UnityEnvironment._generate_step_input": { "total": 5.446890979003456, "count": 18221, "is_parallel": true, "self": 5.446890979003456 }, "communicator.exchange": { "total": 199.48527966299764, "count": 18221, "is_parallel": true, "self": 199.48527966299764 }, "steps_from_proto": { "total": 31.29577772500403, "count": 18221, "is_parallel": true, "self": 6.185652642997411, "children": { "_process_rank_one_or_two_observation": { "total": 25.11012508200662, "count": 182210, "is_parallel": true, "self": 25.11012508200662 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018106299989995023, "count": 1, "self": 0.00018106299989995023, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.6129958280048, "count": 399453, "is_parallel": true, "self": 9.727005452037588, "children": { "process_trajectory": { "total": 246.60433654096784, "count": 399453, "is_parallel": true, "self": 245.45083934896786, "children": { "RLTrainer._checkpoint": { "total": 1.1534971919999748, "count": 4, "is_parallel": true, "self": 1.1534971919999748 } } }, "_update_policy": { "total": 194.28165383499936, "count": 90, "is_parallel": true, "self": 74.4786849539982, "children": { "TorchPPOOptimizer.update": { "total": 119.80296888100116, "count": 4587, "is_parallel": true, "self": 119.80296888100116 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2147430229999827, "count": 1, "self": 0.0011691629999859288, "children": { "RLTrainer._checkpoint": { "total": 0.21357385999999678, "count": 1, "self": 0.21357385999999678 } } } } } } }