{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9539575576782227, "min": 0.9539575576782227, "max": 2.868345022201538, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9139.8671875, "min": 9139.8671875, "max": 29500.9296875, "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": 12.874055862426758, "min": 0.3940783143043518, "max": 12.874055862426758, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.44091796875, "min": 76.4511947631836, "max": 2602.48388671875, "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": 0.06881797554338917, "min": 0.06250238763704877, "max": 0.07909993787144748, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2752719021735567, "min": 0.2596844040748442, "max": 0.3954996893572374, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19052040752242594, "min": 0.13463008363603376, "max": 0.2769418570340848, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7620816300897038, "min": 0.5385203345441351, "max": 1.3847092851704241, "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": 25.636363636363637, "min": 3.522727272727273, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 155.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.522727272727273, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 155.0, "max": 1390.0, "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": "1680842262", "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": "1680842709" }, "total": 447.739271604, "count": 1, "self": 0.4297269319999941, "children": { "run_training.setup": { "total": 0.11565258799998901, "count": 1, "self": 0.11565258799998901 }, "TrainerController.start_learning": { "total": 447.193892084, "count": 1, "self": 0.5337365620010246, "children": { "TrainerController._reset_env": { "total": 3.9572499539999626, "count": 1, "self": 3.9572499539999626 }, "TrainerController.advance": { "total": 442.575711997999, "count": 18205, "self": 0.28436421800250855, "children": { "env_step": { "total": 442.2913477799965, "count": 18205, "self": 324.81302341797846, "children": { "SubprocessEnvManager._take_step": { "total": 117.21089402900304, "count": 18205, "self": 1.6629203299910955, "children": { "TorchPolicy.evaluate": { "total": 115.54797369901195, "count": 18205, "self": 115.54797369901195 } } }, "workers": { "total": 0.26743033301499963, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 445.81596283401484, "count": 18205, "is_parallel": true, "self": 205.46982184901452, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00697931599995627, "count": 1, "is_parallel": true, "self": 0.005570306999970853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014090089999854172, "count": 10, "is_parallel": true, "self": 0.0014090089999854172 } } }, "UnityEnvironment.step": { "total": 0.03661236900001086, "count": 1, "is_parallel": true, "self": 0.0005515860000855355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003659229999470881, "count": 1, "is_parallel": true, "self": 0.0003659229999470881 }, "communicator.exchange": { "total": 0.0338593359999777, "count": 1, "is_parallel": true, "self": 0.0338593359999777 }, "steps_from_proto": { "total": 0.0018355240000005324, "count": 1, "is_parallel": true, "self": 0.00040332099996476245, "children": { "_process_rank_one_or_two_observation": { "total": 0.00143220300003577, "count": 10, "is_parallel": true, "self": 0.00143220300003577 } } } } } } }, "UnityEnvironment.step": { "total": 240.34614098500032, "count": 18204, "is_parallel": true, "self": 9.814437579005755, "children": { "UnityEnvironment._generate_step_input": { "total": 5.270069134994003, "count": 18204, "is_parallel": true, "self": 5.270069134994003 }, "communicator.exchange": { "total": 194.56482976799913, "count": 18204, "is_parallel": true, "self": 194.56482976799913 }, "steps_from_proto": { "total": 30.69680450300143, "count": 18204, "is_parallel": true, "self": 6.040930328006311, "children": { "_process_rank_one_or_two_observation": { "total": 24.65587417499512, "count": 182040, "is_parallel": true, "self": 24.65587417499512 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014133399997717788, "count": 1, "self": 0.00014133399997717788, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 439.1166666509882, "count": 390661, "is_parallel": true, "self": 9.773581667023961, "children": { "process_trajectory": { "total": 241.43560187096443, "count": 390661, "is_parallel": true, "self": 240.04226739896433, "children": { "RLTrainer._checkpoint": { "total": 1.393334472000106, "count": 4, "is_parallel": true, "self": 1.393334472000106 } } }, "_update_policy": { "total": 187.90748311299978, "count": 90, "is_parallel": true, "self": 70.84802872099556, "children": { "TorchPPOOptimizer.update": { "total": 117.05945439200423, "count": 4584, "is_parallel": true, "self": 117.05945439200423 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1270522360000541, "count": 1, "self": 0.0008664580000186106, "children": { "RLTrainer._checkpoint": { "total": 0.1261857780000355, "count": 1, "self": 0.1261857780000355 } } } } } } }