{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1693741083145142, "min": 1.1693741083145142, "max": 2.859534740447998, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11152.3203125, "min": 11152.3203125, "max": 29315.951171875, "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": 12.126372337341309, "min": 0.46520137786865234, "max": 12.126372337341309, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2364.642578125, "min": 90.24906921386719, "max": 2431.15673828125, "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": 0.0636041866170012, "min": 0.06343909434608398, "max": 0.07402307879088124, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2544167464680048, "min": 0.25375637738433593, "max": 0.3701153939544062, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2368920917312304, "min": 0.12949612327308083, "max": 0.2777020598159117, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9475683669249216, "min": 0.5179844930923233, "max": 1.3168682710212818, "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": 23.818181818181817, "min": 3.7045454545454546, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1048.0, "min": 163.0, "max": 1307.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.818181818181817, "min": 3.7045454545454546, "max": 23.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1048.0, "min": 163.0, "max": 1307.0, "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": "1691775358", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691775997" }, "total": 639.203758351, "count": 1, "self": 0.5412505490000967, "children": { "run_training.setup": { "total": 0.07645880499995883, "count": 1, "self": 0.07645880499995883 }, "TrainerController.start_learning": { "total": 638.586048997, "count": 1, "self": 0.8360344080090272, "children": { "TrainerController._reset_env": { "total": 4.622115819999976, "count": 1, "self": 4.622115819999976 }, "TrainerController.advance": { "total": 632.953496908991, "count": 18201, "self": 0.40798909398620253, "children": { "env_step": { "total": 632.5455078150048, "count": 18201, "self": 463.1226132589972, "children": { "SubprocessEnvManager._take_step": { "total": 169.0088404290097, "count": 18201, "self": 2.61340557901633, "children": { "TorchPolicy.evaluate": { "total": 166.39543484999336, "count": 18201, "self": 166.39543484999336 } } }, "workers": { "total": 0.4140541269979394, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 636.3378714059966, "count": 18201, "is_parallel": true, "self": 290.08401099299755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006182949999981702, "count": 1, "is_parallel": true, "self": 0.00435662099982892, "children": { "_process_rank_one_or_two_observation": { "total": 0.001826329000152782, "count": 10, "is_parallel": true, "self": 0.001826329000152782 } } }, "UnityEnvironment.step": { "total": 0.06081518499996719, "count": 1, "is_parallel": true, "self": 0.0005029129999911675, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038914100002784835, "count": 1, "is_parallel": true, "self": 0.00038914100002784835 }, "communicator.exchange": { "total": 0.05716546699994751, "count": 1, "is_parallel": true, "self": 0.05716546699994751 }, "steps_from_proto": { "total": 0.002757664000000659, "count": 1, "is_parallel": true, "self": 0.0004791279999949438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022785360000057153, "count": 10, "is_parallel": true, "self": 0.0022785360000057153 } } } } } } }, "UnityEnvironment.step": { "total": 346.253860412999, "count": 18200, "is_parallel": true, "self": 14.068824250970977, "children": { "UnityEnvironment._generate_step_input": { "total": 7.493292057017527, "count": 18200, "is_parallel": true, "self": 7.493292057017527 }, "communicator.exchange": { "total": 273.12359496200185, "count": 18200, "is_parallel": true, "self": 273.12359496200185 }, "steps_from_proto": { "total": 51.56814914300867, "count": 18200, "is_parallel": true, "self": 9.83822681400909, "children": { "_process_rank_one_or_two_observation": { "total": 41.72992232899958, "count": 182000, "is_parallel": true, "self": 41.72992232899958 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015779399996063148, "count": 1, "self": 0.00015779399996063148, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 627.3118268059889, "count": 600000, "is_parallel": true, "self": 15.266111775027525, "children": { "process_trajectory": { "total": 349.23024307296134, "count": 600000, "is_parallel": true, "self": 347.169533675961, "children": { "RLTrainer._checkpoint": { "total": 2.0607093970003234, "count": 4, "is_parallel": true, "self": 2.0607093970003234 } } }, "_update_policy": { "total": 262.815471958, "count": 90, "is_parallel": true, "self": 104.30377082499865, "children": { "TorchPPOOptimizer.update": { "total": 158.51170113300134, "count": 4587, "is_parallel": true, "self": 158.51170113300134 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1742440660000284, "count": 1, "self": 0.0009736140000313753, "children": { "RLTrainer._checkpoint": { "total": 0.17327045199999702, "count": 1, "self": 0.17327045199999702 } } } } } } }