| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 0.7957099080085754, |
| "min": 0.7957099080085754, |
| "max": 2.8563289642333984, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 7562.4267578125, |
| "min": 7562.4267578125, |
| "max": 29157.40625, |
| "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": 13.244961738586426, |
| "min": 0.40661969780921936, |
| "max": 13.244961738586426, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 2582.767578125, |
| "min": 78.88422393798828, |
| "max": 2698.944091796875, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.06404528001578857, |
| "min": 0.06321780451110623, |
| "max": 0.07678341565113833, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.2561811200631543, |
| "min": 0.2528712180444249, |
| "max": 0.3774720570757328, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.20761064352358088, |
| "min": 0.13143833223205315, |
| "max": 0.3016098103686875, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.8304425740943235, |
| "min": 0.5257533289282126, |
| "max": 1.5080490518434375, |
| "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": 25.84090909090909, |
| "min": 3.6363636363636362, |
| "max": 26.4, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 1137.0, |
| "min": 160.0, |
| "max": 1452.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 25.84090909090909, |
| "min": 3.6363636363636362, |
| "max": 26.4, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 1137.0, |
| "min": 160.0, |
| "max": 1452.0, |
| "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": "1743653949", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/jichuanh/miniconda3/envs/rl-3.10.12/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": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1743654424" |
| }, |
| "total": 474.5750870180782, |
| "count": 1, |
| "self": 0.32164653216023, |
| "children": { |
| "run_training.setup": { |
| "total": 0.020590801956132054, |
| "count": 1, |
| "self": 0.020590801956132054 |
| }, |
| "TrainerController.start_learning": { |
| "total": 474.23284968396183, |
| "count": 1, |
| "self": 0.27560369309503585, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.7312891869805753, |
| "count": 1, |
| "self": 1.7312891869805753 |
| }, |
| "TrainerController.advance": { |
| "total": 472.1544932528632, |
| "count": 18192, |
| "self": 0.2788525018841028, |
| "children": { |
| "env_step": { |
| "total": 358.1379139982164, |
| "count": 18192, |
| "self": 306.8463125395356, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 51.12450114171952, |
| "count": 18192, |
| "self": 0.8916661420371383, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 50.23283499968238, |
| "count": 18192, |
| "self": 50.23283499968238 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.1671003169612959, |
| "count": 18192, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 473.2484598492738, |
| "count": 18192, |
| "is_parallel": true, |
| "self": 194.1853048002813, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0037167060654610395, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000989304156973958, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0027274019084870815, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0027274019084870815 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0418608330655843, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007675740635022521, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005503649590536952, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005503649590536952 |
| }, |
| "communicator.exchange": { |
| "total": 0.03816245496273041, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03816245496273041 |
| }, |
| "steps_from_proto": { |
| "total": 0.002380439080297947, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046900834422558546, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0019114307360723615, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0019114307360723615 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 279.0631550489925, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 12.114476416143589, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 6.768708605435677, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 6.768708605435677 |
| }, |
| "communicator.exchange": { |
| "total": 222.67332780151628, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 222.67332780151628 |
| }, |
| "steps_from_proto": { |
| "total": 37.50664222589694, |
| "count": 18191, |
| "is_parallel": true, |
| "self": 7.064729824895039, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 30.4419124010019, |
| "count": 181910, |
| "is_parallel": true, |
| "self": 30.4419124010019 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 113.73772675276268, |
| "count": 18192, |
| "self": 0.36871410463936627, |
| "children": { |
| "process_trajectory": { |
| "total": 20.287144357920624, |
| "count": 18192, |
| "self": 19.958361598895863, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3287827590247616, |
| "count": 4, |
| "self": 0.3287827590247616 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 93.08186829020269, |
| "count": 90, |
| "self": 28.039598874165677, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 65.04226941603702, |
| "count": 4587, |
| "self": 65.04226941603702 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.459901437163353e-07, |
| "count": 1, |
| "self": 8.459901437163353e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07146270503289998, |
| "count": 1, |
| "self": 0.0005863601109012961, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07087634492199868, |
| "count": 1, |
| "self": 0.07087634492199868 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
