{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8531771898269653, "min": 0.8531771898269653, "max": 2.8469321727752686, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8108.59619140625, "min": 8108.59619140625, "max": 29061.484375, "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": 13.082448959350586, "min": 0.410108357667923, "max": 13.082448959350586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2551.07763671875, "min": 79.56101989746094, "max": 2646.1201171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07690474610460703, "min": 0.0637479308338644, "max": 0.07690474610460703, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3076189844184281, "min": 0.25902576175490943, "max": 0.36101027376842504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20984363628953112, "min": 0.10802403693292838, "max": 0.28673410707829045, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8393745451581245, "min": 0.4320961477317135, "max": 1.3944694618968403, "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": 25.15909090909091, "min": 3.25, "max": 25.87272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 143.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.25, "max": 25.87272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 143.0, "max": 1423.0, "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": "1755428631", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/py310/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": "1755429060" }, "total": 429.1081915740001, "count": 1, "self": 0.43334580800024014, "children": { "run_training.setup": { "total": 0.023837541999910172, "count": 1, "self": 0.023837541999910172 }, "TrainerController.start_learning": { "total": 428.65100822399995, "count": 1, "self": 0.36220684999227615, "children": { "TrainerController._reset_env": { "total": 3.1524677099999963, "count": 1, "self": 3.1524677099999963 }, "TrainerController.advance": { "total": 425.05297755000765, "count": 18192, "self": 0.373407225006531, "children": { "env_step": { "total": 305.6500155219975, "count": 18192, "self": 234.52064169999505, "children": { "SubprocessEnvManager._take_step": { "total": 70.90890765600966, "count": 18192, "self": 1.2770481890293013, "children": { "TorchPolicy.evaluate": { "total": 69.63185946698036, "count": 18192, "self": 69.63185946698036 } } }, "workers": { "total": 0.22046616599277513, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.34090519300844, "count": 18192, "is_parallel": true, "self": 221.16150375700568, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005374402000029477, "count": 1, "is_parallel": true, "self": 0.00371693699980824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016574650002212366, "count": 10, "is_parallel": true, "self": 0.0016574650002212366 } } }, "UnityEnvironment.step": { "total": 0.06363723499998741, "count": 1, "is_parallel": true, "self": 0.000569647999782319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039255600006526947, "count": 1, "is_parallel": true, "self": 0.00039255600006526947 }, "communicator.exchange": { "total": 0.06083827100007966, "count": 1, "is_parallel": true, "self": 0.06083827100007966 }, "steps_from_proto": { "total": 0.001836760000060167, "count": 1, "is_parallel": true, "self": 0.00034215600032894145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014946039997312255, "count": 10, "is_parallel": true, "self": 0.0014946039997312255 } } } } } } }, "UnityEnvironment.step": { "total": 206.17940143600276, "count": 18191, "is_parallel": true, "self": 9.99233756600745, "children": { "UnityEnvironment._generate_step_input": { "total": 5.499454836989912, "count": 18191, "is_parallel": true, "self": 5.499454836989912 }, "communicator.exchange": { "total": 158.5671490880037, "count": 18191, "is_parallel": true, "self": 158.5671490880037 }, "steps_from_proto": { "total": 32.1204599450017, "count": 18191, "is_parallel": true, "self": 5.691391110023119, "children": { "_process_rank_one_or_two_observation": { "total": 26.42906883497858, "count": 181910, "is_parallel": true, "self": 26.42906883497858 } } } } } } } } } } }, "trainer_advance": { "total": 119.02955480300363, "count": 18192, "self": 0.4330421400088653, "children": { "process_trajectory": { "total": 26.999135182994337, "count": 18192, "self": 26.590927561994476, "children": { "RLTrainer._checkpoint": { "total": 0.4082076209998604, "count": 4, "self": 0.4082076209998604 } } }, "_update_policy": { "total": 91.59737748000043, "count": 90, "self": 36.7054528160005, "children": { "TorchPPOOptimizer.update": { "total": 54.89192466399993, "count": 4587, "self": 54.89192466399993 } } } } } } }, "trainer_threads": { "total": 9.709999631013488e-07, "count": 1, "self": 9.709999631013488e-07 }, "TrainerController._save_models": { "total": 0.08335514300006253, "count": 1, "self": 0.0008061720000114292, "children": { "RLTrainer._checkpoint": { "total": 0.0825489710000511, "count": 1, "self": 0.0825489710000511 } } } } } } }