{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8511237502098083, "min": 0.8499658107757568, "max": 2.858919143676758, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8135.89208984375, "min": 8135.89208984375, "max": 29278.19140625, "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": 12.929222106933594, "min": 0.34580230712890625, "max": 12.929222106933594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.1982421875, "min": 67.08564758300781, "max": 2636.3447265625, "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": 0.06815881534476366, "min": 0.06253064110041676, "max": 0.07565992882146555, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27263526137905464, "min": 0.250122564401667, "max": 0.37829964410732775, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18408568028141473, "min": 0.11388058376877441, "max": 0.28169066625482897, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7363427211256589, "min": 0.45552233507509765, "max": 1.408453331274145, "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": 25.295454545454547, "min": 3.5454545454545454, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 156.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.5454545454545454, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 156.0, "max": 1422.0, "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": "1680088159", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680088644" }, "total": 484.65067807699995, "count": 1, "self": 0.4344755910000231, "children": { "run_training.setup": { "total": 0.10732289200001333, "count": 1, "self": 0.10732289200001333 }, "TrainerController.start_learning": { "total": 484.1088795939999, "count": 1, "self": 0.5456887960064591, "children": { "TrainerController._reset_env": { "total": 8.228687008000009, "count": 1, "self": 8.228687008000009 }, "TrainerController.advance": { "total": 475.1869548369934, "count": 18201, "self": 0.2919194559912057, "children": { "env_step": { "total": 474.8950353810022, "count": 18201, "self": 340.921971268007, "children": { "SubprocessEnvManager._take_step": { "total": 133.69884231700837, "count": 18201, "self": 1.8945104150200223, "children": { "TorchPolicy.evaluate": { "total": 131.80433190198835, "count": 18201, "self": 131.80433190198835 } } }, "workers": { "total": 0.2742217959868185, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 482.53709564299993, "count": 18201, "is_parallel": true, "self": 231.74777518701165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00529973200002587, "count": 1, "is_parallel": true, "self": 0.0038652430000070126, "children": { "_process_rank_one_or_two_observation": { "total": 0.001434489000018857, "count": 10, "is_parallel": true, "self": 0.001434489000018857 } } }, "UnityEnvironment.step": { "total": 0.039538675000017065, "count": 1, "is_parallel": true, "self": 0.000625714000022981, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003345480000120915, "count": 1, "is_parallel": true, "self": 0.0003345480000120915 }, "communicator.exchange": { "total": 0.036393735999979526, "count": 1, "is_parallel": true, "self": 0.036393735999979526 }, "steps_from_proto": { "total": 0.0021846770000024662, "count": 1, "is_parallel": true, "self": 0.00045378599998002755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017308910000224387, "count": 10, "is_parallel": true, "self": 0.0017308910000224387 } } } } } } }, "UnityEnvironment.step": { "total": 250.78932045598827, "count": 18200, "is_parallel": true, "self": 9.832483706985784, "children": { "UnityEnvironment._generate_step_input": { "total": 5.605821317003858, "count": 18200, "is_parallel": true, "self": 5.605821317003858 }, "communicator.exchange": { "total": 201.63467231999653, "count": 18200, "is_parallel": true, "self": 201.63467231999653 }, "steps_from_proto": { "total": 33.71634311200211, "count": 18200, "is_parallel": true, "self": 6.780537823984787, "children": { "_process_rank_one_or_two_observation": { "total": 26.93580528801732, "count": 182000, "is_parallel": true, "self": 26.93580528801732 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001131320000240521, "count": 1, "self": 0.0001131320000240521, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.30092848800075, "count": 425090, "is_parallel": true, "self": 11.137250107971454, "children": { "process_trajectory": { "total": 262.5580038720296, "count": 425090, "is_parallel": true, "self": 261.3853277740297, "children": { "RLTrainer._checkpoint": { "total": 1.1726760979998971, "count": 4, "is_parallel": true, "self": 1.1726760979998971 } } }, "_update_policy": { "total": 197.6056745079997, "count": 90, "is_parallel": true, "self": 73.48487122399968, "children": { "TorchPPOOptimizer.update": { "total": 124.12080328400003, "count": 4587, "is_parallel": true, "self": 124.12080328400003 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1474358210000446, "count": 1, "self": 0.0009122280000610772, "children": { "RLTrainer._checkpoint": { "total": 0.14652359299998352, "count": 1, "self": 0.14652359299998352 } } } } } } }