| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 0.8283047676086426, |
| "min": 0.8150866031646729, |
| "max": 2.8552048206329346, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 7872.20849609375, |
| "min": 7872.20849609375, |
| "max": 29145.9296875, |
| "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": 12.115374565124512, |
| "min": 0.3154679238796234, |
| "max": 12.115374565124512, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 2362.498046875, |
| "min": 61.200775146484375, |
| "max": 2463.9658203125, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.06511272728276513, |
| "min": 0.05987404672481467, |
| "max": 0.0739144747664013, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.2604509091310605, |
| "min": 0.25561320608910904, |
| "max": 0.3627322874803498, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.15451937935808127, |
| "min": 0.12109309006094313, |
| "max": 0.2864453225013088, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.6180775174323251, |
| "min": 0.4843723602437725, |
| "max": 1.421846362889982, |
| "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.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.Environment.CumulativeReward.mean": { |
| "value": 23.136363636363637, |
| "min": 3.2954545454545454, |
| "max": 23.963636363636365, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 1018.0, |
| "min": 145.0, |
| "max": 1318.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 23.136363636363637, |
| "min": 3.2954545454545454, |
| "max": 23.963636363636365, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 1018.0, |
| "min": 145.0, |
| "max": 1318.0, |
| "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": "1775554479", |
| "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", |
| "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": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1775554958" |
| }, |
| "total": 479.63809118100016, |
| "count": 1, |
| "self": 0.4339957290001166, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0235608030000094, |
| "count": 1, |
| "self": 0.0235608030000094 |
| }, |
| "TrainerController.start_learning": { |
| "total": 479.18053464900004, |
| "count": 1, |
| "self": 0.39308492799432315, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.637276101999987, |
| "count": 1, |
| "self": 3.637276101999987 |
| }, |
| "TrainerController.advance": { |
| "total": 475.0672188310059, |
| "count": 18192, |
| "self": 0.42320599300228423, |
| "children": { |
| "env_step": { |
| "total": 346.545823024994, |
| "count": 18192, |
| "self": 268.98222378398805, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 77.32251871601193, |
| "count": 18192, |
| "self": 1.3814555529831978, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 75.94106316302873, |
| "count": 18192, |
| "self": 75.94106316302873 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.241080524994004, |
| "count": 18192, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 477.3700036459836, |
| "count": 18192, |
| "is_parallel": true, |
| "self": 241.0601697809932, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.004958819999956177, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0034994079994703498, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014594120004858269, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0014594120004858269 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.037905982999973276, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008687300000929099, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004777749998083891, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004777749998083891 |
| }, |
| "communicator.exchange": { |
| "total": 0.03446473300004982, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03446473300004982 |
| }, |
| "steps_from_proto": { |
| "total": 0.002094745000022158, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003955570002744935, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016991879997476644, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0016991879997476644 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 236.30983386499042, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 11.092854659987324, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 5.997917467004754, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 5.997917467004754 |
| }, |
| "communicator.exchange": { |
| "total": 178.13588363799454, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 178.13588363799454 |
| }, |
| "steps_from_proto": { |
| "total": 41.083178100003806, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 7.133757655971522, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 33.949420444032285, |
| "count": 181910, |
| "is_parallel": true, |
| "self": 33.949420444032285 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 128.09818981300964, |
| "count": 18192, |
| "self": 0.47939574800057017, |
| "children": { |
| "process_trajectory": { |
| "total": 29.13621502301021, |
| "count": 18192, |
| "self": 28.711784283010047, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.4244307400001617, |
| "count": 4, |
| "self": 0.4244307400001617 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 98.48257904199886, |
| "count": 90, |
| "self": 39.94298601798482, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 58.53959302401404, |
| "count": 4587, |
| "self": 58.53959302401404 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.949999366654083e-07, |
| "count": 1, |
| "self": 9.949999366654083e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08295379299988781, |
| "count": 1, |
| "self": 0.0008237949998601835, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08212999800002763, |
| "count": 1, |
| "self": 0.08212999800002763 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
