{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8799859881401062, "min": 0.8670602440834045, "max": 2.8241145610809326, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8363.38671875, "min": 8363.38671875, "max": 28828.560546875, "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": 13.140066146850586, "min": 0.3569025993347168, "max": 13.296059608459473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2562.31298828125, "min": 69.23910522460938, "max": 2711.83642578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07364543404358247, "min": 0.06495794705109552, "max": 0.07376124866632203, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29458173617432987, "min": 0.2598317882043821, "max": 0.36880624333161016, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19076050109430856, "min": 0.1333495317307739, "max": 0.308365344782086, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7630420043772342, "min": 0.5333981269230956, "max": 1.535982504194858, "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.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.Environment.CumulativeReward.mean": { "value": 25.863636363636363, "min": 3.6818181818181817, "max": 26.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 162.0, "max": 1448.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 3.6818181818181817, "max": 26.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 162.0, "max": 1448.0, "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": "1741947383", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741947804" }, "total": 421.0808077500001, "count": 1, "self": 0.644501345000208, "children": { "run_training.setup": { "total": 0.02311853699995936, "count": 1, "self": 0.02311853699995936 }, "TrainerController.start_learning": { "total": 420.4131878679999, "count": 1, "self": 0.3295254529950853, "children": { "TrainerController._reset_env": { "total": 3.124714784000048, "count": 1, "self": 3.124714784000048 }, "TrainerController.advance": { "total": 416.82639454200444, "count": 18192, "self": 0.34576984799912225, "children": { "env_step": { "total": 293.8093449989958, "count": 18192, "self": 223.6033539629948, "children": { "SubprocessEnvManager._take_step": { "total": 70.00854592800681, "count": 18192, "self": 1.2210750730066593, "children": { "TorchPolicy.evaluate": { "total": 68.78747085500015, "count": 18192, "self": 68.78747085500015 } } }, "workers": { "total": 0.19744510799421278, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 418.8938520730047, "count": 18192, "is_parallel": true, "self": 222.6904907290085, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005621632000043064, "count": 1, "is_parallel": true, "self": 0.003987471000186815, "children": { "_process_rank_one_or_two_observation": { "total": 0.001634160999856249, "count": 10, "is_parallel": true, "self": 0.001634160999856249 } } }, "UnityEnvironment.step": { "total": 0.034166408999908526, "count": 1, "is_parallel": true, "self": 0.0007257649997427507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040883300005134515, "count": 1, "is_parallel": true, "self": 0.00040883300005134515 }, "communicator.exchange": { "total": 0.031245456000078775, "count": 1, "is_parallel": true, "self": 0.031245456000078775 }, "steps_from_proto": { "total": 0.0017863550000356554, "count": 1, "is_parallel": true, "self": 0.0003438079999114052, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014425470001242502, "count": 10, "is_parallel": true, "self": 0.0014425470001242502 } } } } } } }, "UnityEnvironment.step": { "total": 196.20336134399622, "count": 18191, "is_parallel": true, "self": 9.65589231001934, "children": { "UnityEnvironment._generate_step_input": { "total": 5.265614880990597, "count": 18191, "is_parallel": true, "self": 5.265614880990597 }, "communicator.exchange": { "total": 150.5864106969873, "count": 18191, "is_parallel": true, "self": 150.5864106969873 }, "steps_from_proto": { "total": 30.695443455998998, "count": 18191, "is_parallel": true, "self": 5.413442928015911, "children": { "_process_rank_one_or_two_observation": { "total": 25.282000527983087, "count": 181910, "is_parallel": true, "self": 25.282000527983087 } } } } } } } } } } }, "trainer_advance": { "total": 122.6712796950095, "count": 18192, "self": 0.3953791030107823, "children": { "process_trajectory": { "total": 26.936400021998566, "count": 18192, "self": 26.398614800998644, "children": { "RLTrainer._checkpoint": { "total": 0.5377852209999219, "count": 4, "self": 0.5377852209999219 } } }, "_update_policy": { "total": 95.33950057000015, "count": 90, "self": 37.90641661900145, "children": { "TorchPPOOptimizer.update": { "total": 57.43308395099871, "count": 4587, "self": 57.43308395099871 } } } } } } }, "trainer_threads": { "total": 1.142000201070914e-06, "count": 1, "self": 1.142000201070914e-06 }, "TrainerController._save_models": { "total": 0.13255194700013817, "count": 1, "self": 0.0012535770001704805, "children": { "RLTrainer._checkpoint": { "total": 0.1312983699999677, "count": 1, "self": 0.1312983699999677 } } } } } } }