{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9085586667060852, "min": 0.9085586667060852, "max": 2.866291046142578, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8684.912109375, "min": 8684.912109375, "max": 29353.6875, "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": 13.011411666870117, "min": 0.44429418444633484, "max": 13.011411666870117, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.225341796875, "min": 86.19306945800781, "max": 2652.5615234375, "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": 0.06527389555769475, "min": 0.06177048085596385, "max": 0.07606235380814064, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.261095582230779, "min": 0.2551089690989066, "max": 0.3803117690407032, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18997904610838373, "min": 0.15153897261046168, "max": 0.2772818033163454, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7599161844335349, "min": 0.6061558904418467, "max": 1.3567825289917927, "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": 25.75, "min": 4.159090909090909, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 183.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 4.159090909090909, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 183.0, "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": "1702462101", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702462584" }, "total": 482.4734629169998, "count": 1, "self": 0.44064801999957126, "children": { "run_training.setup": { "total": 0.06368457100006708, "count": 1, "self": 0.06368457100006708 }, "TrainerController.start_learning": { "total": 481.96913032600014, "count": 1, "self": 0.5960956859871658, "children": { "TrainerController._reset_env": { "total": 4.368685722999999, "count": 1, "self": 4.368685722999999 }, "TrainerController.advance": { "total": 476.9144964680131, "count": 18200, "self": 0.2881096299656747, "children": { "env_step": { "total": 476.62638683804744, "count": 18200, "self": 321.9885999710791, "children": { "SubprocessEnvManager._take_step": { "total": 154.34377860896575, "count": 18200, "self": 1.5456759749295088, "children": { "TorchPolicy.evaluate": { "total": 152.79810263403624, "count": 18200, "self": 152.79810263403624 } } }, "workers": { "total": 0.29400825800257735, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 480.6382443620023, "count": 18200, "is_parallel": true, "self": 237.11363594001796, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006993968999722711, "count": 1, "is_parallel": true, "self": 0.004875319999882777, "children": { "_process_rank_one_or_two_observation": { "total": 0.002118648999839934, "count": 10, "is_parallel": true, "self": 0.002118648999839934 } } }, "UnityEnvironment.step": { "total": 0.03409795200013832, "count": 1, "is_parallel": true, "self": 0.0006313560002126906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026347199991505477, "count": 1, "is_parallel": true, "self": 0.00026347199991505477 }, "communicator.exchange": { "total": 0.03119661200025803, "count": 1, "is_parallel": true, "self": 0.03119661200025803 }, "steps_from_proto": { "total": 0.002006511999752547, "count": 1, "is_parallel": true, "self": 0.00041111999917120556, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015953920005813416, "count": 10, "is_parallel": true, "self": 0.0015953920005813416 } } } } } } }, "UnityEnvironment.step": { "total": 243.52460842198434, "count": 18199, "is_parallel": true, "self": 10.653626790990074, "children": { "UnityEnvironment._generate_step_input": { "total": 5.432542552976429, "count": 18199, "is_parallel": true, "self": 5.432542552976429 }, "communicator.exchange": { "total": 193.18527047299858, "count": 18199, "is_parallel": true, "self": 193.18527047299858 }, "steps_from_proto": { "total": 34.253168605019255, "count": 18199, "is_parallel": true, "self": 6.6031031230613735, "children": { "_process_rank_one_or_two_observation": { "total": 27.65006548195788, "count": 181990, "is_parallel": true, "self": 27.65006548195788 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016638199986118707, "count": 1, "self": 0.00016638199986118707, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.9731327340496, "count": 502679, "is_parallel": true, "self": 10.765007480117674, "children": { "process_trajectory": { "total": 266.87502646893154, "count": 502679, "is_parallel": true, "self": 265.88159057993244, "children": { "RLTrainer._checkpoint": { "total": 0.9934358889991017, "count": 4, "is_parallel": true, "self": 0.9934358889991017 } } }, "_update_policy": { "total": 195.3330987850004, "count": 90, "is_parallel": true, "self": 59.79864995401658, "children": { "TorchPPOOptimizer.update": { "total": 135.53444883098382, "count": 4587, "is_parallel": true, "self": 135.53444883098382 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08968606700000237, "count": 1, "self": 0.0008969760001491522, "children": { "RLTrainer._checkpoint": { "total": 0.08878909099985322, "count": 1, "self": 0.08878909099985322 } } } } } } }