{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9624238014221191, "min": 0.9470034837722778, "max": 2.858245372772217, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9189.22265625, "min": 9189.22265625, "max": 29334.171875, "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": 12.950430870056152, "min": 0.36621251702308655, "max": 12.950430870056152, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.333984375, "min": 71.04522705078125, "max": 2635.6181640625, "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": 0.06831877421281402, "min": 0.0652333117322711, "max": 0.0739343137689752, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27327509685125606, "min": 0.26250545701437733, "max": 0.36720650635959146, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23240924129883447, "min": 0.1069182485961766, "max": 0.27911587432026863, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9296369651953379, "min": 0.4276729943847064, "max": 1.3115650599493702, "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": 25.818181818181817, "min": 3.25, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 143.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.25, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 143.0, "max": 1415.0, "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": "1687755199", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687755657" }, "total": 457.60042025999996, "count": 1, "self": 0.38679502799988086, "children": { "run_training.setup": { "total": 0.040586217999987184, "count": 1, "self": 0.040586217999987184 }, "TrainerController.start_learning": { "total": 457.1730390140001, "count": 1, "self": 0.5302396980096091, "children": { "TrainerController._reset_env": { "total": 4.048631748999981, "count": 1, "self": 4.048631748999981 }, "TrainerController.advance": { "total": 452.4629052479906, "count": 18202, "self": 0.2615370149875389, "children": { "env_step": { "total": 452.20136823300305, "count": 18202, "self": 331.4805684290044, "children": { "SubprocessEnvManager._take_step": { "total": 120.45511038300023, "count": 18202, "self": 1.7868419519902545, "children": { "TorchPolicy.evaluate": { "total": 118.66826843100998, "count": 18202, "self": 118.66826843100998 } } }, "workers": { "total": 0.2656894209984557, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 455.5372212179995, "count": 18202, "is_parallel": true, "self": 214.9146297340009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006241146999997227, "count": 1, "is_parallel": true, "self": 0.0042287910000027296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020123559999944973, "count": 10, "is_parallel": true, "self": 0.0020123559999944973 } } }, "UnityEnvironment.step": { "total": 0.043563513999998804, "count": 1, "is_parallel": true, "self": 0.0006086249999555093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003876160000118034, "count": 1, "is_parallel": true, "self": 0.0003876160000118034 }, "communicator.exchange": { "total": 0.040330373000017516, "count": 1, "is_parallel": true, "self": 0.040330373000017516 }, "steps_from_proto": { "total": 0.002236900000013975, "count": 1, "is_parallel": true, "self": 0.0003780540000377641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018588459999762108, "count": 10, "is_parallel": true, "self": 0.0018588459999762108 } } } } } } }, "UnityEnvironment.step": { "total": 240.6225914839986, "count": 18201, "is_parallel": true, "self": 10.195768979008704, "children": { "UnityEnvironment._generate_step_input": { "total": 5.181217124990297, "count": 18201, "is_parallel": true, "self": 5.181217124990297 }, "communicator.exchange": { "total": 191.5662335309962, "count": 18201, "is_parallel": true, "self": 191.5662335309962 }, "steps_from_proto": { "total": 33.67937184900342, "count": 18201, "is_parallel": true, "self": 6.0922890940088905, "children": { "_process_rank_one_or_two_observation": { "total": 27.587082754994526, "count": 182010, "is_parallel": true, "self": 27.587082754994526 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011105099997621437, "count": 1, "self": 0.00011105099997621437, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.0592842549831, "count": 419606, "is_parallel": true, "self": 9.42849909697594, "children": { "process_trajectory": { "total": 245.04658097000657, "count": 419606, "is_parallel": true, "self": 243.97454064900654, "children": { "RLTrainer._checkpoint": { "total": 1.0720403210000313, "count": 4, "is_parallel": true, "self": 1.0720403210000313 } } }, "_update_policy": { "total": 194.58420418800057, "count": 90, "is_parallel": true, "self": 74.22155527799902, "children": { "TorchPPOOptimizer.update": { "total": 120.36264891000155, "count": 4587, "is_parallel": true, "self": 120.36264891000155 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1311512679999396, "count": 1, "self": 0.0008224890000292362, "children": { "RLTrainer._checkpoint": { "total": 0.13032877899991036, "count": 1, "self": 0.13032877899991036 } } } } } } }