{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8651920557022095, "min": 0.8523612022399902, "max": 2.8740010261535645, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8279.8876953125, "min": 8279.8876953125, "max": 29401.029296875, "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": 12.522505760192871, "min": 0.3638897240161896, "max": 12.52877426147461, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2441.888671875, "min": 70.5946044921875, "max": 2555.869873046875, "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": 0.06259346365439734, "min": 0.06255198740380401, "max": 0.07434596892277363, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2503738546175894, "min": 0.25020794961521603, "max": 0.36708153742844896, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20776893717108985, "min": 0.12567587055530693, "max": 0.3196186223158649, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8310757486843594, "min": 0.5027034822212277, "max": 1.5016098129289117, "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": 24.477272727272727, "min": 3.6363636363636362, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 160.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 3.6363636363636362, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 160.0, "max": 1370.0, "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": "1688700820", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688701311" }, "total": 490.800143774, "count": 1, "self": 0.4316293919999339, "children": { "run_training.setup": { "total": 0.04252697400002603, "count": 1, "self": 0.04252697400002603 }, "TrainerController.start_learning": { "total": 490.325987408, "count": 1, "self": 0.6520620690052965, "children": { "TrainerController._reset_env": { "total": 4.192583184, "count": 1, "self": 4.192583184 }, "TrainerController.advance": { "total": 485.33756374199464, "count": 18204, "self": 0.3217913209924177, "children": { "env_step": { "total": 485.0157724210022, "count": 18204, "self": 354.5796261739994, "children": { "SubprocessEnvManager._take_step": { "total": 130.12360594000555, "count": 18204, "self": 2.0692647820065133, "children": { "TorchPolicy.evaluate": { "total": 128.05434115799903, "count": 18204, "self": 128.05434115799903 } } }, "workers": { "total": 0.31254030699730606, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 488.4018560430036, "count": 18204, "is_parallel": true, "self": 224.17367479400622, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005478624000005539, "count": 1, "is_parallel": true, "self": 0.003760557000020981, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017180669999845577, "count": 10, "is_parallel": true, "self": 0.0017180669999845577 } } }, "UnityEnvironment.step": { "total": 0.04340403500000889, "count": 1, "is_parallel": true, "self": 0.00045465100004093983, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032256599999413993, "count": 1, "is_parallel": true, "self": 0.00032256599999413993 }, "communicator.exchange": { "total": 0.04061275599997316, "count": 1, "is_parallel": true, "self": 0.04061275599997316 }, "steps_from_proto": { "total": 0.0020140620000006493, "count": 1, "is_parallel": true, "self": 0.0003402859999823704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016737760000182789, "count": 10, "is_parallel": true, "self": 0.0016737760000182789 } } } } } } }, "UnityEnvironment.step": { "total": 264.2281812489974, "count": 18203, "is_parallel": true, "self": 10.932735793989508, "children": { "UnityEnvironment._generate_step_input": { "total": 5.466403400007152, "count": 18203, "is_parallel": true, "self": 5.466403400007152 }, "communicator.exchange": { "total": 211.65751243200293, "count": 18203, "is_parallel": true, "self": 211.65751243200293 }, "steps_from_proto": { "total": 36.17152962299778, "count": 18203, "is_parallel": true, "self": 6.735939079007807, "children": { "_process_rank_one_or_two_observation": { "total": 29.435590543989974, "count": 182030, "is_parallel": true, "self": 29.435590543989974 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015533200007666892, "count": 1, "self": 0.00015533200007666892, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.74200125804015, "count": 475801, "is_parallel": true, "self": 10.128154182054175, "children": { "process_trajectory": { "total": 267.8717545559862, "count": 475801, "is_parallel": true, "self": 266.3726373989862, "children": { "RLTrainer._checkpoint": { "total": 1.4991171569999437, "count": 4, "is_parallel": true, "self": 1.4991171569999437 } } }, "_update_policy": { "total": 203.74209251999977, "count": 90, "is_parallel": true, "self": 75.32750616000109, "children": { "TorchPPOOptimizer.update": { "total": 128.41458635999868, "count": 4584, "is_parallel": true, "self": 128.41458635999868 } } } } } } } } }, "TrainerController._save_models": { "total": 0.143623080999987, "count": 1, "self": 0.0009553270000424163, "children": { "RLTrainer._checkpoint": { "total": 0.14266775399994458, "count": 1, "self": 0.14266775399994458 } } } } } } }