{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0423314571380615, "min": 1.0423314571380615, "max": 2.8652639389038086, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9952.1806640625, "min": 9952.1806640625, "max": 29343.16796875, "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": 12.666844367980957, "min": 0.2232806235551834, "max": 12.666844367980957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2470.03466796875, "min": 43.31644058227539, "max": 2555.735595703125, "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": 0.0695247304883749, "min": 0.060870599414431806, "max": 0.07988163151198487, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2780989219534996, "min": 0.24348239765772722, "max": 0.3994081575599243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21761701906136438, "min": 0.11544847586100884, "max": 0.26586336166250935, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8704680762454575, "min": 0.46179390344403537, "max": 1.3293168083125468, "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": 25.25, "min": 3.1818181818181817, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 140.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.1818181818181817, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 140.0, "max": 1364.0, "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": "1673921723", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1673922159" }, "total": 435.4905329609999, "count": 1, "self": 0.3886569099998951, "children": { "run_training.setup": { "total": 0.11255746999995608, "count": 1, "self": 0.11255746999995608 }, "TrainerController.start_learning": { "total": 434.989318581, "count": 1, "self": 0.4977012910061376, "children": { "TrainerController._reset_env": { "total": 9.962395570000012, "count": 1, "self": 9.962395570000012 }, "TrainerController.advance": { "total": 424.40716293399385, "count": 18201, "self": 0.25178511898809575, "children": { "env_step": { "total": 424.15537781500575, "count": 18201, "self": 275.86352720000286, "children": { "SubprocessEnvManager._take_step": { "total": 148.0226278290022, "count": 18201, "self": 1.3680511540121643, "children": { "TorchPolicy.evaluate": { "total": 146.65457667499004, "count": 18201, "self": 32.07760376898591, "children": { "TorchPolicy.sample_actions": { "total": 114.57697290600413, "count": 18201, "self": 114.57697290600413 } } } } }, "workers": { "total": 0.2692227860006824, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 433.81701941499784, "count": 18201, "is_parallel": true, "self": 211.83559626198723, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00693607300001986, "count": 1, "is_parallel": true, "self": 0.004475235999962024, "children": { "_process_rank_one_or_two_observation": { "total": 0.002460837000057836, "count": 10, "is_parallel": true, "self": 0.002460837000057836 } } }, "UnityEnvironment.step": { "total": 0.045214852000071915, "count": 1, "is_parallel": true, "self": 0.0005489420000230893, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023410199992213165, "count": 1, "is_parallel": true, "self": 0.00023410199992213165 }, "communicator.exchange": { "total": 0.042419921000032446, "count": 1, "is_parallel": true, "self": 0.042419921000032446 }, "steps_from_proto": { "total": 0.002011887000094248, "count": 1, "is_parallel": true, "self": 0.0004613660001950848, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015505209998991631, "count": 10, "is_parallel": true, "self": 0.0015505209998991631 } } } } } } }, "UnityEnvironment.step": { "total": 221.9814231530106, "count": 18200, "is_parallel": true, "self": 8.497541111017654, "children": { "UnityEnvironment._generate_step_input": { "total": 5.100900909981306, "count": 18200, "is_parallel": true, "self": 5.100900909981306 }, "communicator.exchange": { "total": 174.5741815780117, "count": 18200, "is_parallel": true, "self": 174.5741815780117 }, "steps_from_proto": { "total": 33.80879955399996, "count": 18200, "is_parallel": true, "self": 6.763789570051017, "children": { "_process_rank_one_or_two_observation": { "total": 27.045009983948944, "count": 182000, "is_parallel": true, "self": 27.045009983948944 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.136500001550303e-05, "count": 1, "self": 4.136500001550303e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 421.098494248008, "count": 345538, "is_parallel": true, "self": 9.297369928018838, "children": { "process_trajectory": { "total": 239.8242410979883, "count": 345538, "is_parallel": true, "self": 239.14811319798844, "children": { "RLTrainer._checkpoint": { "total": 0.6761278999998694, "count": 4, "is_parallel": true, "self": 0.6761278999998694 } } }, "_update_policy": { "total": 171.97688322200088, "count": 90, "is_parallel": true, "self": 45.66122384800258, "children": { "TorchPPOOptimizer.update": { "total": 126.3156593739983, "count": 4587, "is_parallel": true, "self": 126.3156593739983 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12201742100000956, "count": 1, "self": 0.0008411679998516775, "children": { "RLTrainer._checkpoint": { "total": 0.12117625300015789, "count": 1, "self": 0.12117625300015789 } } } } } } }