{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0076357126235962, "min": 1.0076357126235962, "max": 2.8541014194488525, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9620.90625, "min": 9620.90625, "max": 29228.853515625, "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": 1.2503714561462402, "min": 0.11449915915727615, "max": 1.2569438219070435, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 243.8224334716797, "min": 22.21283721923828, "max": 255.97384643554688, "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": 0.06537453140624042, "min": 0.06079026495689166, "max": 0.07255646927874562, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26149812562496166, "min": 0.24316105982756664, "max": 0.36206743187344104, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10795289358379795, "min": 0.043170824423820406, "max": 0.11508442762435651, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4318115743351918, "min": 0.17268329769528162, "max": 0.5754221381217826, "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": 24.75, "min": 3.2954545454545454, "max": 24.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 145.0, "max": 1353.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 3.2954545454545454, "max": 24.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 145.0, "max": 1353.0, "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": "1687336504", "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": "1687336961" }, "total": 457.6743351670001, "count": 1, "self": 0.38502534600013405, "children": { "run_training.setup": { "total": 0.04004001800001333, "count": 1, "self": 0.04004001800001333 }, "TrainerController.start_learning": { "total": 457.24926980299995, "count": 1, "self": 0.5385772319938269, "children": { "TrainerController._reset_env": { "total": 4.060846866999896, "count": 1, "self": 4.060846866999896 }, "TrainerController.advance": { "total": 452.5134801930061, "count": 18202, "self": 0.24959090201070921, "children": { "env_step": { "total": 452.2638892909954, "count": 18202, "self": 331.93087227898627, "children": { "SubprocessEnvManager._take_step": { "total": 120.07621832500104, "count": 18202, "self": 1.9188470700026983, "children": { "TorchPolicy.evaluate": { "total": 118.15737125499834, "count": 18202, "self": 118.15737125499834 } } }, "workers": { "total": 0.25679868700808584, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 455.5438302870066, "count": 18202, "is_parallel": true, "self": 213.67731299701074, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005608143000017662, "count": 1, "is_parallel": true, "self": 0.003908295999963229, "children": { "_process_rank_one_or_two_observation": { "total": 0.001699847000054433, "count": 10, "is_parallel": true, "self": 0.001699847000054433 } } }, "UnityEnvironment.step": { "total": 0.03421949099993071, "count": 1, "is_parallel": true, "self": 0.0005817009999873335, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003506189999598064, "count": 1, "is_parallel": true, "self": 0.0003506189999598064 }, "communicator.exchange": { "total": 0.0312768710000455, "count": 1, "is_parallel": true, "self": 0.0312768710000455 }, "steps_from_proto": { "total": 0.00201029999993807, "count": 1, "is_parallel": true, "self": 0.00036989000011544704, "children": { "_process_rank_one_or_two_observation": { "total": 0.001640409999822623, "count": 10, "is_parallel": true, "self": 0.001640409999822623 } } } } } } }, "UnityEnvironment.step": { "total": 241.86651728999584, "count": 18201, "is_parallel": true, "self": 10.169303139990461, "children": { "UnityEnvironment._generate_step_input": { "total": 5.166734137998446, "count": 18201, "is_parallel": true, "self": 5.166734137998446 }, "communicator.exchange": { "total": 192.65408182500903, "count": 18201, "is_parallel": true, "self": 192.65408182500903 }, "steps_from_proto": { "total": 33.8763981869979, "count": 18201, "is_parallel": true, "self": 6.07507280794016, "children": { "_process_rank_one_or_two_observation": { "total": 27.801325379057744, "count": 182010, "is_parallel": true, "self": 27.801325379057744 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011680600005092856, "count": 1, "self": 0.00011680600005092856, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.0632430999626, "count": 430333, "is_parallel": true, "self": 9.277428346986653, "children": { "process_trajectory": { "total": 245.28750594697613, "count": 430333, "is_parallel": true, "self": 244.17181640297622, "children": { "RLTrainer._checkpoint": { "total": 1.1156895439999062, "count": 4, "is_parallel": true, "self": 1.1156895439999062 } } }, "_update_policy": { "total": 194.49830880599984, "count": 90, "is_parallel": true, "self": 76.03361529999768, "children": { "TorchPPOOptimizer.update": { "total": 118.46469350600216, "count": 4587, "is_parallel": true, "self": 118.46469350600216 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1362487050000709, "count": 1, "self": 0.0008559890002288739, "children": { "RLTrainer._checkpoint": { "total": 0.13539271599984204, "count": 1, "self": 0.13539271599984204 } } } } } } }