{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0418094396591187, "min": 1.0418094396591187, "max": 2.869569778442383, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9958.65625, "min": 9958.65625, "max": 29418.830078125, "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": 3.244004726409912, "min": 0.2468123733997345, "max": 3.289792537689209, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 632.5809326171875, "min": 47.88159942626953, "max": 671.11767578125, "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": 0.08213037610346197, "min": 0.061931782804529954, "max": 0.08213037610346197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32852150441384786, "min": 0.2515959333401292, "max": 0.35989651603592265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13669459908908488, "min": 0.07092703425886986, "max": 0.1804005631921338, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5467783963563395, "min": 0.2837081370354794, "max": 0.902002815960669, "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": 25.113636363636363, "min": 3.340909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 147.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.340909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 147.0, "max": 1416.0, "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": "1694361570", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1694362044" }, "total": 474.09764435400007, "count": 1, "self": 0.43879868299995906, "children": { "run_training.setup": { "total": 0.050433600000019396, "count": 1, "self": 0.050433600000019396 }, "TrainerController.start_learning": { "total": 473.6084120710001, "count": 1, "self": 0.5287956059959242, "children": { "TrainerController._reset_env": { "total": 4.111921808000034, "count": 1, "self": 4.111921808000034 }, "TrainerController.advance": { "total": 468.8068168850041, "count": 18202, "self": 0.26554160399371085, "children": { "env_step": { "total": 468.54127528101037, "count": 18202, "self": 338.7847168100013, "children": { "SubprocessEnvManager._take_step": { "total": 129.48651321400575, "count": 18202, "self": 1.775788676016532, "children": { "TorchPolicy.evaluate": { "total": 127.71072453798922, "count": 18202, "self": 127.71072453798922 } } }, "workers": { "total": 0.2700452570032894, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 472.006937222984, "count": 18202, "is_parallel": true, "self": 225.52672415598454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005329957000071772, "count": 1, "is_parallel": true, "self": 0.0037195839998958036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016103730001759686, "count": 10, "is_parallel": true, "self": 0.0016103730001759686 } } }, "UnityEnvironment.step": { "total": 0.03553185800001302, "count": 1, "is_parallel": true, "self": 0.0005935309999358651, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003214620001017465, "count": 1, "is_parallel": true, "self": 0.0003214620001017465 }, "communicator.exchange": { "total": 0.032459896999966986, "count": 1, "is_parallel": true, "self": 0.032459896999966986 }, "steps_from_proto": { "total": 0.002156968000008419, "count": 1, "is_parallel": true, "self": 0.0004918780000480183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016650899999604007, "count": 10, "is_parallel": true, "self": 0.0016650899999604007 } } } } } } }, "UnityEnvironment.step": { "total": 246.48021306699945, "count": 18201, "is_parallel": true, "self": 10.46068463996994, "children": { "UnityEnvironment._generate_step_input": { "total": 5.297590162000347, "count": 18201, "is_parallel": true, "self": 5.297590162000347 }, "communicator.exchange": { "total": 194.71006556402517, "count": 18201, "is_parallel": true, "self": 194.71006556402517 }, "steps_from_proto": { "total": 36.011872701003995, "count": 18201, "is_parallel": true, "self": 6.41911206197085, "children": { "_process_rank_one_or_two_observation": { "total": 29.592760639033145, "count": 182010, "is_parallel": true, "self": 29.592760639033145 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023249700006999774, "count": 1, "self": 0.00023249700006999774, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.09248803704986, "count": 443431, "is_parallel": true, "self": 9.707918761098199, "children": { "process_trajectory": { "total": 253.97204841495238, "count": 443431, "is_parallel": true, "self": 252.6160176399527, "children": { "RLTrainer._checkpoint": { "total": 1.356030774999681, "count": 4, "is_parallel": true, "self": 1.356030774999681 } } }, "_update_policy": { "total": 201.41252086099928, "count": 90, "is_parallel": true, "self": 80.23861788299871, "children": { "TorchPPOOptimizer.update": { "total": 121.17390297800057, "count": 4587, "is_parallel": true, "self": 121.17390297800057 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16064527499997894, "count": 1, "self": 0.0010970519999773387, "children": { "RLTrainer._checkpoint": { "total": 0.1595482230000016, "count": 1, "self": 0.1595482230000016 } } } } } } }