{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9602072238922119, "min": 0.9602072238922119, "max": 2.8766801357269287, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9168.05859375, "min": 9168.05859375, "max": 29460.080078125, "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": 12.834735870361328, "min": 0.3413277864456177, "max": 12.834735870361328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2502.7734375, "min": 66.21759033203125, "max": 2562.05419921875, "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": 0.07070010742637689, "min": 0.06165821417537291, "max": 0.07646433737129116, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28280042970550756, "min": 0.24752596196234594, "max": 0.3583786295068921, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19421952356602634, "min": 0.1213780276879084, "max": 0.3191233681259202, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7768780942641054, "min": 0.4855121107516336, "max": 1.4818815480844647, "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": 25.772727272727273, "min": 3.227272727272727, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 142.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.227272727272727, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 142.0, "max": 1403.0, "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": "1717208484", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717208916" }, "total": 431.850682346, "count": 1, "self": 0.4322024489999876, "children": { "run_training.setup": { "total": 0.05689095799993993, "count": 1, "self": 0.05689095799993993 }, "TrainerController.start_learning": { "total": 431.36158893900006, "count": 1, "self": 0.5105942389945994, "children": { "TrainerController._reset_env": { "total": 3.0062653580000642, "count": 1, "self": 3.0062653580000642 }, "TrainerController.advance": { "total": 427.75619387300526, "count": 18201, "self": 0.23641667800495725, "children": { "env_step": { "total": 427.5197771950003, "count": 18201, "self": 279.09768105700584, "children": { "SubprocessEnvManager._take_step": { "total": 148.1672892239867, "count": 18201, "self": 1.3863413569659997, "children": { "TorchPolicy.evaluate": { "total": 146.7809478670207, "count": 18201, "self": 146.7809478670207 } } }, "workers": { "total": 0.2548069140077587, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 430.1732322300113, "count": 18201, "is_parallel": true, "self": 217.74803804002408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005495355999983076, "count": 1, "is_parallel": true, "self": 0.003923261999943861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015720940000392147, "count": 10, "is_parallel": true, "self": 0.0015720940000392147 } } }, "UnityEnvironment.step": { "total": 0.036060130999999274, "count": 1, "is_parallel": true, "self": 0.0006613179999703789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040047699997103337, "count": 1, "is_parallel": true, "self": 0.00040047699997103337 }, "communicator.exchange": { "total": 0.03298916700009613, "count": 1, "is_parallel": true, "self": 0.03298916700009613 }, "steps_from_proto": { "total": 0.00200916899996173, "count": 1, "is_parallel": true, "self": 0.00041860000010274234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015905689998589878, "count": 10, "is_parallel": true, "self": 0.0015905689998589878 } } } } } } }, "UnityEnvironment.step": { "total": 212.42519418998722, "count": 18200, "is_parallel": true, "self": 9.769901717977973, "children": { "UnityEnvironment._generate_step_input": { "total": 5.009119535997343, "count": 18200, "is_parallel": true, "self": 5.009119535997343 }, "communicator.exchange": { "total": 165.83597971300776, "count": 18200, "is_parallel": true, "self": 165.83597971300776 }, "steps_from_proto": { "total": 31.81019322300415, "count": 18200, "is_parallel": true, "self": 5.7867003769952134, "children": { "_process_rank_one_or_two_observation": { "total": 26.023492846008935, "count": 182000, "is_parallel": true, "self": 26.023492846008935 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001635300000089046, "count": 1, "self": 0.0001635300000089046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 422.8162887639918, "count": 626160, "is_parallel": true, "self": 12.593767299899582, "children": { "process_trajectory": { "total": 234.1747551350926, "count": 626160, "is_parallel": true, "self": 233.51784005309253, "children": { "RLTrainer._checkpoint": { "total": 0.6569150820000687, "count": 4, "is_parallel": true, "self": 0.6569150820000687 } } }, "_update_policy": { "total": 176.04776632899961, "count": 90, "is_parallel": true, "self": 57.01516714300192, "children": { "TorchPPOOptimizer.update": { "total": 119.0325991859977, "count": 4587, "is_parallel": true, "self": 119.0325991859977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08837193900012608, "count": 1, "self": 0.0009554460002618725, "children": { "RLTrainer._checkpoint": { "total": 0.0874164929998642, "count": 1, "self": 0.0874164929998642 } } } } } } }