{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9179381132125854, "min": 0.9122137427330017, "max": 2.856472969055176, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8774.5703125, "min": 8774.5703125, "max": 29347.404296875, "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": 13.115577697753906, "min": 0.34806567430496216, "max": 13.115577697753906, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2557.53759765625, "min": 67.52474212646484, "max": 2639.87646484375, "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": 0.07267930566141492, "min": 0.06363644242443187, "max": 0.07763563742549855, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2907172226456597, "min": 0.25454576969772746, "max": 0.35781422461307144, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19700773564331672, "min": 0.11541882095237573, "max": 0.2787599592086147, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7880309425732669, "min": 0.4616752838095029, "max": 1.3580914490363176, "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": 25.84090909090909, "min": 3.25, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 143.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 3.25, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 143.0, "max": 1428.0, "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": "1676637320", "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": "1676637829" }, "total": 509.204087339, "count": 1, "self": 0.8155613600000606, "children": { "run_training.setup": { "total": 0.11121727300007933, "count": 1, "self": 0.11121727300007933 }, "TrainerController.start_learning": { "total": 508.27730870599987, "count": 1, "self": 0.7064343880031174, "children": { "TrainerController._reset_env": { "total": 10.355530464000026, "count": 1, "self": 10.355530464000026 }, "TrainerController.advance": { "total": 496.99563600599663, "count": 18206, "self": 0.320549323000364, "children": { "env_step": { "total": 496.67508668299627, "count": 18206, "self": 343.82608187300286, "children": { "SubprocessEnvManager._take_step": { "total": 152.5169816689795, "count": 18206, "self": 1.686396258977311, "children": { "TorchPolicy.evaluate": { "total": 150.8305854100022, "count": 18206, "self": 34.56247778598322, "children": { "TorchPolicy.sample_actions": { "total": 116.26810762401897, "count": 18206, "self": 116.26810762401897 } } } } }, "workers": { "total": 0.33202314101390584, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 506.31668818198716, "count": 18206, "is_parallel": true, "self": 238.50278601999878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006678368000052615, "count": 1, "is_parallel": true, "self": 0.004043153999987226, "children": { "_process_rank_one_or_two_observation": { "total": 0.002635214000065389, "count": 10, "is_parallel": true, "self": 0.002635214000065389 } } }, "UnityEnvironment.step": { "total": 0.04170776300009038, "count": 1, "is_parallel": true, "self": 0.0005490520001103505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002636420000499129, "count": 1, "is_parallel": true, "self": 0.0002636420000499129 }, "communicator.exchange": { "total": 0.03863040499993531, "count": 1, "is_parallel": true, "self": 0.03863040499993531 }, "steps_from_proto": { "total": 0.0022646639999948093, "count": 1, "is_parallel": true, "self": 0.0004634429999441636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018012210000506457, "count": 10, "is_parallel": true, "self": 0.0018012210000506457 } } } } } } }, "UnityEnvironment.step": { "total": 267.8139021619884, "count": 18205, "is_parallel": true, "self": 10.578603629977124, "children": { "UnityEnvironment._generate_step_input": { "total": 5.729722544992342, "count": 18205, "is_parallel": true, "self": 5.729722544992342 }, "communicator.exchange": { "total": 214.2306916340001, "count": 18205, "is_parallel": true, "self": 214.2306916340001 }, "steps_from_proto": { "total": 37.27488435301882, "count": 18205, "is_parallel": true, "self": 8.271555000966373, "children": { "_process_rank_one_or_two_observation": { "total": 29.003329352052447, "count": 182050, "is_parallel": true, "self": 29.003329352052447 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010727600010795868, "count": 1, "self": 0.00010727600010795868, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.20019113799015, "count": 464193, "is_parallel": true, "self": 11.792126954040668, "children": { "process_trajectory": { "total": 284.9710953109485, "count": 464193, "is_parallel": true, "self": 283.6412135709485, "children": { "RLTrainer._checkpoint": { "total": 1.329881740000019, "count": 4, "is_parallel": true, "self": 1.329881740000019 } } }, "_update_policy": { "total": 196.43696887300098, "count": 90, "is_parallel": true, "self": 66.11533531098621, "children": { "TorchPPOOptimizer.update": { "total": 130.32163356201477, "count": 4587, "is_parallel": true, "self": 130.32163356201477 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21960057199999028, "count": 1, "self": 0.0013909869999224611, "children": { "RLTrainer._checkpoint": { "total": 0.21820958500006782, "count": 1, "self": 0.21820958500006782 } } } } } } }