{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8691062331199646, "min": 0.8689799904823303, "max": 2.866596221923828, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8298.2265625, "min": 8298.2265625, "max": 29356.8125, "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": 13.028643608093262, "min": 0.38476845622062683, "max": 13.028643608093262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.58544921875, "min": 74.64508056640625, "max": 2643.21142578125, "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": 0.07231253409226351, "min": 0.0636768387078465, "max": 0.07676385443012217, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28925013636905406, "min": 0.254707354831386, "max": 0.3573315426819688, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19547678084642278, "min": 0.11280615172832839, "max": 0.2869029680887858, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7819071233856911, "min": 0.45122460691331356, "max": 1.434514840443929, "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": 25.568181818181817, "min": 3.477272727272727, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 153.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.477272727272727, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 153.0, "max": 1408.0, "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": "1674330165", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674330593" }, "total": 428.34839337899996, "count": 1, "self": 0.3786162339998782, "children": { "run_training.setup": { "total": 0.10380363400008719, "count": 1, "self": 0.10380363400008719 }, "TrainerController.start_learning": { "total": 427.865973511, "count": 1, "self": 0.503693328988561, "children": { "TrainerController._reset_env": { "total": 5.841857254000047, "count": 1, "self": 5.841857254000047 }, "TrainerController.advance": { "total": 421.39675431301134, "count": 18201, "self": 0.26198879301716715, "children": { "env_step": { "total": 421.1347655199942, "count": 18201, "self": 273.84091711300107, "children": { "SubprocessEnvManager._take_step": { "total": 147.03426086800607, "count": 18201, "self": 1.4093753470023103, "children": { "TorchPolicy.evaluate": { "total": 145.62488552100376, "count": 18201, "self": 32.65183797099496, "children": { "TorchPolicy.sample_actions": { "total": 112.9730475500088, "count": 18201, "self": 112.9730475500088 } } } } }, "workers": { "total": 0.25958753898703435, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 426.64422966701034, "count": 18201, "is_parallel": true, "self": 204.30932852201522, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019681689999515584, "count": 1, "is_parallel": true, "self": 0.000686633999634978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012815350003165804, "count": 10, "is_parallel": true, "self": 0.0012815350003165804 } } }, "UnityEnvironment.step": { "total": 0.03586977699990257, "count": 1, "is_parallel": true, "self": 0.0004913190000479517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038622699992174603, "count": 1, "is_parallel": true, "self": 0.00038622699992174603 }, "communicator.exchange": { "total": 0.033058229999937794, "count": 1, "is_parallel": true, "self": 0.033058229999937794 }, "steps_from_proto": { "total": 0.001934000999995078, "count": 1, "is_parallel": true, "self": 0.00043541900004129275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014985819999537853, "count": 10, "is_parallel": true, "self": 0.0014985819999537853 } } } } } } }, "UnityEnvironment.step": { "total": 222.33490114499511, "count": 18200, "is_parallel": true, "self": 8.26086385701467, "children": { "UnityEnvironment._generate_step_input": { "total": 4.949579959995276, "count": 18200, "is_parallel": true, "self": 4.949579959995276 }, "communicator.exchange": { "total": 176.52198657299607, "count": 18200, "is_parallel": true, "self": 176.52198657299607 }, "steps_from_proto": { "total": 32.6024707549891, "count": 18200, "is_parallel": true, "self": 6.549216821974937, "children": { "_process_rank_one_or_two_observation": { "total": 26.05325393301416, "count": 182000, "is_parallel": true, "self": 26.05325393301416 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.847600002402032e-05, "count": 1, "self": 6.847600002402032e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 418.4073096179927, "count": 344132, "is_parallel": true, "self": 9.084630050032047, "children": { "process_trajectory": { "total": 241.40101821296025, "count": 344132, "is_parallel": true, "self": 240.61480438796013, "children": { "RLTrainer._checkpoint": { "total": 0.786213825000118, "count": 4, "is_parallel": true, "self": 0.786213825000118 } } }, "_update_policy": { "total": 167.92166135500042, "count": 90, "is_parallel": true, "self": 42.20432269400567, "children": { "TorchPPOOptimizer.update": { "total": 125.71733866099476, "count": 4587, "is_parallel": true, "self": 125.71733866099476 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12360013900001832, "count": 1, "self": 0.0008107809999273741, "children": { "RLTrainer._checkpoint": { "total": 0.12278935800009094, "count": 1, "self": 0.12278935800009094 } } } } } } }