{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9417535662651062, "min": 0.9417535662651062, "max": 2.8511414527893066, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8950.42578125, "min": 8950.42578125, "max": 29104.451171875, "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": 13.088232040405273, "min": 0.3055339455604553, "max": 13.088232040405273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2552.205322265625, "min": 59.27358627319336, "max": 2646.385009765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0736931969323789, "min": 0.06312362433755861, "max": 0.07432544121540702, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2947727877295156, "min": 0.25249449735023444, "max": 0.3611641473903814, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20727793580176784, "min": 0.10630417836935022, "max": 0.2884298411800581, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8291117432070714, "min": 0.42521671347740086, "max": 1.426711762360498, "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": 26.15909090909091, "min": 3.0681818181818183, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1151.0, "min": 135.0, "max": 1435.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.15909090909091, "min": 3.0681818181818183, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1151.0, "min": 135.0, "max": 1435.0, "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": "1757544786", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "command_line_arguments": "/home/ladong/Workspace/huggingface-rl/huggingface/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": "1757545063" }, "total": 276.2807822649993, "count": 1, "self": 0.26877565199720266, "children": { "run_training.setup": { "total": 0.017116151000664104, "count": 1, "self": 0.017116151000664104 }, "TrainerController.start_learning": { "total": 275.9948904620014, "count": 1, "self": 0.29574019011488417, "children": { "TrainerController._reset_env": { "total": 1.9565269710001303, "count": 1, "self": 1.9565269710001303 }, "TrainerController.advance": { "total": 273.6896985628864, "count": 18192, "self": 0.274560586842199, "children": { "env_step": { "total": 193.7547592650044, "count": 18192, "self": 144.92709763807397, "children": { "SubprocessEnvManager._take_step": { "total": 48.64560025800711, "count": 18192, "self": 0.7697358399946097, "children": { "TorchPolicy.evaluate": { "total": 47.8758644180125, "count": 18192, "self": 47.8758644180125 } } }, "workers": { "total": 0.18206136892331415, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 275.4847219540534, "count": 18192, "is_parallel": true, "self": 148.23092025404367, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.015490389998376486, "count": 1, "is_parallel": true, "self": 0.01448687899937795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010035109989985358, "count": 10, "is_parallel": true, "self": 0.0010035109989985358 } } }, "UnityEnvironment.step": { "total": 0.017947192000065115, "count": 1, "is_parallel": true, "self": 0.00022118599918030668, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001706080001895316, "count": 1, "is_parallel": true, "self": 0.0001706080001895316 }, "communicator.exchange": { "total": 0.01678198599984171, "count": 1, "is_parallel": true, "self": 0.01678198599984171 }, "steps_from_proto": { "total": 0.0007734120008535683, "count": 1, "is_parallel": true, "self": 0.00015957899813656695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006138330027170014, "count": 10, "is_parallel": true, "self": 0.0006138330027170014 } } } } } } }, "UnityEnvironment.step": { "total": 127.25380170000972, "count": 18191, "is_parallel": true, "self": 4.848363981278453, "children": { "UnityEnvironment._generate_step_input": { "total": 2.623649713874329, "count": 18191, "is_parallel": true, "self": 2.623649713874329 }, "communicator.exchange": { "total": 104.88949614494231, "count": 18191, "is_parallel": true, "self": 104.88949614494231 }, "steps_from_proto": { "total": 14.892291859914621, "count": 18191, "is_parallel": true, "self": 2.917310840986829, "children": { "_process_rank_one_or_two_observation": { "total": 11.974981018927792, "count": 181910, "is_parallel": true, "self": 11.974981018927792 } } } } } } } } } } }, "trainer_advance": { "total": 79.66037871103981, "count": 18192, "self": 0.33689227905597363, "children": { "process_trajectory": { "total": 16.850710433987842, "count": 18192, "self": 16.57884120298695, "children": { "RLTrainer._checkpoint": { "total": 0.2718692310008919, "count": 4, "self": 0.2718692310008919 } } }, "_update_policy": { "total": 62.472775997995996, "count": 90, "self": 25.333497895022447, "children": { "TorchPPOOptimizer.update": { "total": 37.13927810297355, "count": 4587, "self": 37.13927810297355 } } } } } } }, "trainer_threads": { "total": 5.870006134500727e-07, "count": 1, "self": 5.870006134500727e-07 }, "TrainerController._save_models": { "total": 0.052924150999388075, "count": 1, "self": 0.0004205710010865005, "children": { "RLTrainer._checkpoint": { "total": 0.052503579998301575, "count": 1, "self": 0.052503579998301575 } } } } } } }