{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8951179385185242, "min": 0.8951179385185242, "max": 2.864962577819824, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8556.4326171875, "min": 8556.4326171875, "max": 29340.08203125, "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": 13.168647766113281, "min": 0.47584617137908936, "max": 13.168647766113281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.88623046875, "min": 92.31415557861328, "max": 2667.927490234375, "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": 0.06092638506793175, "min": 0.06092638506793175, "max": 0.07263898735662794, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.243705540271727, "min": 0.243705540271727, "max": 0.3631949367831397, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2074889713058285, "min": 0.1326451398404863, "max": 0.28508304649708316, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.829955885223314, "min": 0.5305805593619451, "max": 1.425415232485416, "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": 25.75, "min": 3.909090909090909, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 172.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.909090909090909, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 172.0, "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": "1682427828", "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": "1682428278" }, "total": 449.868548339, "count": 1, "self": 0.4261308879997614, "children": { "run_training.setup": { "total": 0.12558479600011196, "count": 1, "self": 0.12558479600011196 }, "TrainerController.start_learning": { "total": 449.3168326550001, "count": 1, "self": 0.5545285739922292, "children": { "TrainerController._reset_env": { "total": 4.153419658999837, "count": 1, "self": 4.153419658999837 }, "TrainerController.advance": { "total": 444.470377803008, "count": 18201, "self": 0.2726779580004859, "children": { "env_step": { "total": 444.1976998450075, "count": 18201, "self": 323.9943296609647, "children": { "SubprocessEnvManager._take_step": { "total": 119.92939606402024, "count": 18201, "self": 1.7114493400492847, "children": { "TorchPolicy.evaluate": { "total": 118.21794672397095, "count": 18201, "self": 118.21794672397095 } } }, "workers": { "total": 0.27397412002255805, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 448.0145882360159, "count": 18201, "is_parallel": true, "self": 206.77308916100606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005589838999867425, "count": 1, "is_parallel": true, "self": 0.004193426999790972, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013964120000764524, "count": 10, "is_parallel": true, "self": 0.0013964120000764524 } } }, "UnityEnvironment.step": { "total": 0.1307158760000675, "count": 1, "is_parallel": true, "self": 0.0006445269998494041, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004014630001165642, "count": 1, "is_parallel": true, "self": 0.0004014630001165642 }, "communicator.exchange": { "total": 0.12755677900008777, "count": 1, "is_parallel": true, "self": 0.12755677900008777 }, "steps_from_proto": { "total": 0.0021131070000137697, "count": 1, "is_parallel": true, "self": 0.0004008929997780797, "children": { "_process_rank_one_or_two_observation": { "total": 0.00171221400023569, "count": 10, "is_parallel": true, "self": 0.00171221400023569 } } } } } } }, "UnityEnvironment.step": { "total": 241.24149907500987, "count": 18200, "is_parallel": true, "self": 9.70053018997828, "children": { "UnityEnvironment._generate_step_input": { "total": 5.235789420008132, "count": 18200, "is_parallel": true, "self": 5.235789420008132 }, "communicator.exchange": { "total": 194.05116602200246, "count": 18200, "is_parallel": true, "self": 194.05116602200246 }, "steps_from_proto": { "total": 32.254013443020995, "count": 18200, "is_parallel": true, "self": 6.2851167739684115, "children": { "_process_rank_one_or_two_observation": { "total": 25.968896669052583, "count": 182000, "is_parallel": true, "self": 25.968896669052583 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011588500001380453, "count": 1, "self": 0.00011588500001380453, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.94736624789766, "count": 405882, "is_parallel": true, "self": 10.204162963942963, "children": { "process_trajectory": { "total": 244.81044395595427, "count": 405882, "is_parallel": true, "self": 243.75792124895452, "children": { "RLTrainer._checkpoint": { "total": 1.0525227069997527, "count": 4, "is_parallel": true, "self": 1.0525227069997527 } } }, "_update_policy": { "total": 185.93275932800043, "count": 90, "is_parallel": true, "self": 63.731023267010414, "children": { "TorchPPOOptimizer.update": { "total": 122.20173606099002, "count": 4587, "is_parallel": true, "self": 122.20173606099002 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13839073400004054, "count": 1, "self": 0.0008762420000039128, "children": { "RLTrainer._checkpoint": { "total": 0.13751449200003663, "count": 1, "self": 0.13751449200003663 } } } } } } }