{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.859076738357544, "min": 0.859076738357544, "max": 2.868004083633423, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8202.46484375, "min": 8202.46484375, "max": 29371.23046875, "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": 13.031513214111328, "min": 0.4968254566192627, "max": 13.031513214111328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2541.14501953125, "min": 96.38414001464844, "max": 2630.301513671875, "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": 0.06757998167863571, "min": 0.06495233834197742, "max": 0.07433333317840508, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27031992671454286, "min": 0.25980935336790967, "max": 0.3716666658920254, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.174351408164583, "min": 0.1272521649701886, "max": 0.2975895953382931, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.697405632658332, "min": 0.5090086598807544, "max": 1.3822510236618564, "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": 26.045454545454547, "min": 3.75, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 165.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.75, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 165.0, "max": 1394.0, "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": "1683037916", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683038540" }, "total": 623.65981431, "count": 1, "self": 0.48576756600004956, "children": { "run_training.setup": { "total": 0.05461241800003336, "count": 1, "self": 0.05461241800003336 }, "TrainerController.start_learning": { "total": 623.1194343259999, "count": 1, "self": 0.8257884520113521, "children": { "TrainerController._reset_env": { "total": 4.737699007000003, "count": 1, "self": 4.737699007000003 }, "TrainerController.advance": { "total": 617.3962842119885, "count": 18200, "self": 0.4094329389889708, "children": { "env_step": { "total": 616.9868512729995, "count": 18200, "self": 450.278029519991, "children": { "SubprocessEnvManager._take_step": { "total": 166.31937450500362, "count": 18200, "self": 2.9884318519926296, "children": { "TorchPolicy.evaluate": { "total": 163.330942653011, "count": 18200, "self": 163.330942653011 } } }, "workers": { "total": 0.38944724800489894, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 620.6918342659977, "count": 18200, "is_parallel": true, "self": 281.0009056009923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006209531000024526, "count": 1, "is_parallel": true, "self": 0.0045170530000291365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016924779999953898, "count": 10, "is_parallel": true, "self": 0.0016924779999953898 } } }, "UnityEnvironment.step": { "total": 0.0409909809999931, "count": 1, "is_parallel": true, "self": 0.0006781880000517049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044386799999074356, "count": 1, "is_parallel": true, "self": 0.00044386799999074356 }, "communicator.exchange": { "total": 0.037140065999949456, "count": 1, "is_parallel": true, "self": 0.037140065999949456 }, "steps_from_proto": { "total": 0.0027288590000011936, "count": 1, "is_parallel": true, "self": 0.000472637000029863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022562219999713307, "count": 10, "is_parallel": true, "self": 0.0022562219999713307 } } } } } } }, "UnityEnvironment.step": { "total": 339.6909286650054, "count": 18199, "is_parallel": true, "self": 13.45096314398944, "children": { "UnityEnvironment._generate_step_input": { "total": 6.981609920004644, "count": 18199, "is_parallel": true, "self": 6.981609920004644 }, "communicator.exchange": { "total": 274.8492576750004, "count": 18199, "is_parallel": true, "self": 274.8492576750004 }, "steps_from_proto": { "total": 44.40909792601093, "count": 18199, "is_parallel": true, "self": 9.054475058042783, "children": { "_process_rank_one_or_two_observation": { "total": 35.354622867968146, "count": 181990, "is_parallel": true, "self": 35.354622867968146 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019845700001042132, "count": 1, "self": 0.00019845700001042132, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 611.6700950309981, "count": 595686, "is_parallel": true, "self": 15.30084190198545, "children": { "process_trajectory": { "total": 342.62277724701335, "count": 595686, "is_parallel": true, "self": 341.18478638501324, "children": { "RLTrainer._checkpoint": { "total": 1.437990862000106, "count": 4, "is_parallel": true, "self": 1.437990862000106 } } }, "_update_policy": { "total": 253.74647588199934, "count": 90, "is_parallel": true, "self": 93.77673570900237, "children": { "TorchPPOOptimizer.update": { "total": 159.96974017299698, "count": 4587, "is_parallel": true, "self": 159.96974017299698 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15946419800002332, "count": 1, "self": 0.0011644259999457063, "children": { "RLTrainer._checkpoint": { "total": 0.1582997720000776, "count": 1, "self": 0.1582997720000776 } } } } } } }