{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.861574113368988, "min": 0.861574113368988, "max": 2.874605417251587, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8226.3095703125, "min": 8226.3095703125, "max": 29438.833984375, "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": 12.55103874206543, "min": 0.3442811369895935, "max": 12.55103874206543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2447.45263671875, "min": 66.79054260253906, "max": 2552.24169921875, "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": 0.062032111871767305, "min": 0.062032111871767305, "max": 0.07453062052103204, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24812844748706922, "min": 0.24812844748706922, "max": 0.35260499818319024, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2048183851966671, "min": 0.11656293735095281, "max": 0.3085526378131381, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8192735407866684, "min": 0.46625174940381126, "max": 1.5427631890656903, "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": 24.295454545454547, "min": 3.5, "max": 25.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1069.0, "min": 154.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.295454545454547, "min": 3.5, "max": 25.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1069.0, "min": 154.0, "max": 1386.0, "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": "1714662628", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714663139" }, "total": 510.666314872, "count": 1, "self": 0.5020642349999775, "children": { "run_training.setup": { "total": 0.08842375300002914, "count": 1, "self": 0.08842375300002914 }, "TrainerController.start_learning": { "total": 510.075826884, "count": 1, "self": 0.7295689190087842, "children": { "TrainerController._reset_env": { "total": 3.3819310650000034, "count": 1, "self": 3.3819310650000034 }, "TrainerController.advance": { "total": 505.8588748739911, "count": 18199, "self": 0.34927372599202045, "children": { "env_step": { "total": 505.5096011479991, "count": 18199, "self": 331.05099005700725, "children": { "SubprocessEnvManager._take_step": { "total": 174.10039863999526, "count": 18199, "self": 1.783463652991088, "children": { "TorchPolicy.evaluate": { "total": 172.31693498700417, "count": 18199, "self": 172.31693498700417 } } }, "workers": { "total": 0.35821245099657517, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 508.55251713699147, "count": 18199, "is_parallel": true, "self": 249.64273569699617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00859989799999994, "count": 1, "is_parallel": true, "self": 0.0037968290000094385, "children": { "_process_rank_one_or_two_observation": { "total": 0.004803068999990501, "count": 10, "is_parallel": true, "self": 0.004803068999990501 } } }, "UnityEnvironment.step": { "total": 0.03772825900000498, "count": 1, "is_parallel": true, "self": 0.000729941000031431, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004271399999993264, "count": 1, "is_parallel": true, "self": 0.0004271399999993264 }, "communicator.exchange": { "total": 0.03444748599997638, "count": 1, "is_parallel": true, "self": 0.03444748599997638 }, "steps_from_proto": { "total": 0.0021236919999978454, "count": 1, "is_parallel": true, "self": 0.0003929330000005393, "children": { "_process_rank_one_or_two_observation": { "total": 0.001730758999997306, "count": 10, "is_parallel": true, "self": 0.001730758999997306 } } } } } } }, "UnityEnvironment.step": { "total": 258.9097814399953, "count": 18198, "is_parallel": true, "self": 12.294598714999779, "children": { "UnityEnvironment._generate_step_input": { "total": 6.243195714009744, "count": 18198, "is_parallel": true, "self": 6.243195714009744 }, "communicator.exchange": { "total": 201.92784129399155, "count": 18198, "is_parallel": true, "self": 201.92784129399155 }, "steps_from_proto": { "total": 38.44414571699423, "count": 18198, "is_parallel": true, "self": 7.52037716804432, "children": { "_process_rank_one_or_two_observation": { "total": 30.92376854894991, "count": 181980, "is_parallel": true, "self": 30.92376854894991 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.123999997318606e-05, "count": 1, "self": 4.123999997318606e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 499.4058194370134, "count": 786596, "is_parallel": true, "self": 16.60503356001567, "children": { "process_trajectory": { "total": 276.48250190599737, "count": 786596, "is_parallel": true, "self": 275.84383062499734, "children": { "RLTrainer._checkpoint": { "total": 0.638671281000029, "count": 4, "is_parallel": true, "self": 0.638671281000029 } } }, "_update_policy": { "total": 206.31828397100037, "count": 90, "is_parallel": true, "self": 61.73177329299671, "children": { "TorchPPOOptimizer.update": { "total": 144.58651067800366, "count": 4587, "is_parallel": true, "self": 144.58651067800366 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10541078600010678, "count": 1, "self": 0.001117221000072277, "children": { "RLTrainer._checkpoint": { "total": 0.1042935650000345, "count": 1, "self": 0.1042935650000345 } } } } } } }