{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9539939761161804, "min": 0.9539939761161804, "max": 2.860322952270508, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9108.734375, "min": 9108.734375, "max": 29292.568359375, "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": 12.85737419128418, "min": 0.23201611638069153, "max": 12.85737419128418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2507.18798828125, "min": 45.01112747192383, "max": 2603.625, "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": 0.07154430940464211, "min": 0.06451756833726083, "max": 0.07583000868965195, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28617723761856845, "min": 0.2664229421004397, "max": 0.373809511599236, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2142198290310654, "min": 0.11078798406364798, "max": 0.27789474521197527, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8568793161242616, "min": 0.4431519362545919, "max": 1.3894737260598764, "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": 25.318181818181817, "min": 3.340909090909091, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 147.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.340909090909091, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 147.0, "max": 1398.0, "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": "1676670462", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1676671072" }, "total": 609.7145221810001, "count": 1, "self": 0.5967618130000574, "children": { "run_training.setup": { "total": 0.15235236700004862, "count": 1, "self": 0.15235236700004862 }, "TrainerController.start_learning": { "total": 608.965408001, "count": 1, "self": 0.9455813749848403, "children": { "TrainerController._reset_env": { "total": 8.809705441999995, "count": 1, "self": 8.809705441999995 }, "TrainerController.advance": { "total": 599.0453725290151, "count": 18202, "self": 0.4712168260123235, "children": { "env_step": { "total": 598.5741557030028, "count": 18202, "self": 469.60974222501784, "children": { "SubprocessEnvManager._take_step": { "total": 128.54306210099253, "count": 18202, "self": 2.742260564003459, "children": { "TorchPolicy.evaluate": { "total": 125.80080153698907, "count": 18202, "self": 21.64640259098769, "children": { "TorchPolicy.sample_actions": { "total": 104.15439894600138, "count": 18202, "self": 104.15439894600138 } } } } }, "workers": { "total": 0.4213513769924475, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 606.8106719629914, "count": 18202, "is_parallel": true, "self": 269.6226184300099, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008767983999973694, "count": 1, "is_parallel": true, "self": 0.004880936000176916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038870479997967777, "count": 10, "is_parallel": true, "self": 0.0038870479997967777 } } }, "UnityEnvironment.step": { "total": 0.05195237800000996, "count": 1, "is_parallel": true, "self": 0.0007119769999235359, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004707800000005591, "count": 1, "is_parallel": true, "self": 0.0004707800000005591 }, "communicator.exchange": { "total": 0.048271647000092344, "count": 1, "is_parallel": true, "self": 0.048271647000092344 }, "steps_from_proto": { "total": 0.002497973999993519, "count": 1, "is_parallel": true, "self": 0.0005572330001086812, "children": { "_process_rank_one_or_two_observation": { "total": 0.001940740999884838, "count": 10, "is_parallel": true, "self": 0.001940740999884838 } } } } } } }, "UnityEnvironment.step": { "total": 337.1880535329815, "count": 18201, "is_parallel": true, "self": 14.149307702967008, "children": { "UnityEnvironment._generate_step_input": { "total": 7.783288457009007, "count": 18201, "is_parallel": true, "self": 7.783288457009007 }, "communicator.exchange": { "total": 267.7337216719933, "count": 18201, "is_parallel": true, "self": 267.7337216719933 }, "steps_from_proto": { "total": 47.521735701012176, "count": 18201, "is_parallel": true, "self": 11.138049373982426, "children": { "_process_rank_one_or_two_observation": { "total": 36.38368632702975, "count": 182010, "is_parallel": true, "self": 36.38368632702975 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002782000001388951, "count": 1, "self": 0.0002782000001388951, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 592.7742633221078, "count": 694667, "is_parallel": true, "self": 17.80371124204669, "children": { "process_trajectory": { "total": 323.04155529806053, "count": 694667, "is_parallel": true, "self": 321.69845106806065, "children": { "RLTrainer._checkpoint": { "total": 1.3431042299998808, "count": 4, "is_parallel": true, "self": 1.3431042299998808 } } }, "_update_policy": { "total": 251.92899678200058, "count": 90, "is_parallel": true, "self": 86.16877930100566, "children": { "TorchPPOOptimizer.update": { "total": 165.76021748099492, "count": 4587, "is_parallel": true, "self": 165.76021748099492 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16447045499990054, "count": 1, "self": 0.001338257000043086, "children": { "RLTrainer._checkpoint": { "total": 0.16313219799985745, "count": 1, "self": 0.16313219799985745 } } } } } } }