{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8015038371086121, "min": 0.8015038371086121, "max": 2.8675551414489746, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7617.49267578125, "min": 7617.49267578125, "max": 29272.00390625, "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": 12.543980598449707, "min": 0.1506275236606598, "max": 12.543980598449707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2446.076171875, "min": 29.221738815307617, "max": 2537.10888671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06966668747219384, "min": 0.06337783957538241, "max": 0.07691876358439556, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2786667498887754, "min": 0.2559229565716426, "max": 0.357356525107296, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19673457442253242, "min": 0.08362069945239152, "max": 0.27371538725553773, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7869382976901297, "min": 0.3344827978095661, "max": 1.3685769362776887, "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": 24.545454545454547, "min": 2.3636363636363638, "max": 24.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 104.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 2.3636363636363638, "max": 24.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 104.0, "max": 1366.0, "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": "1751496970", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751497399" }, "total": 429.5952069949999, "count": 1, "self": 0.43989403799992033, "children": { "run_training.setup": { "total": 0.022455804000060198, "count": 1, "self": 0.022455804000060198 }, "TrainerController.start_learning": { "total": 429.1328571529999, "count": 1, "self": 0.36627570100779394, "children": { "TrainerController._reset_env": { "total": 3.3669369169999754, "count": 1, "self": 3.3669369169999754 }, "TrainerController.advance": { "total": 425.31502359199203, "count": 18192, "self": 0.387649979994535, "children": { "env_step": { "total": 306.53629263400455, "count": 18192, "self": 236.03172366100887, "children": { "SubprocessEnvManager._take_step": { "total": 70.28690484399988, "count": 18192, "self": 1.2463444850193355, "children": { "TorchPolicy.evaluate": { "total": 69.04056035898054, "count": 18192, "self": 69.04056035898054 } } }, "workers": { "total": 0.217664128995807, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.7199174790014, "count": 18192, "is_parallel": true, "self": 220.5594868420004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053875400000151785, "count": 1, "is_parallel": true, "self": 0.003931650000026821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014558899999883579, "count": 10, "is_parallel": true, "self": 0.0014558899999883579 } } }, "UnityEnvironment.step": { "total": 0.03526551799996014, "count": 1, "is_parallel": true, "self": 0.0005651239999906466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000458438999999089, "count": 1, "is_parallel": true, "self": 0.000458438999999089 }, "communicator.exchange": { "total": 0.03231397900003685, "count": 1, "is_parallel": true, "self": 0.03231397900003685 }, "steps_from_proto": { "total": 0.001927975999933551, "count": 1, "is_parallel": true, "self": 0.0003900949996022973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015378810003312537, "count": 10, "is_parallel": true, "self": 0.0015378810003312537 } } } } } } }, "UnityEnvironment.step": { "total": 207.160430637001, "count": 18191, "is_parallel": true, "self": 9.857337980023658, "children": { "UnityEnvironment._generate_step_input": { "total": 5.379704244991331, "count": 18191, "is_parallel": true, "self": 5.379704244991331 }, "communicator.exchange": { "total": 160.06169333399396, "count": 18191, "is_parallel": true, "self": 160.06169333399396 }, "steps_from_proto": { "total": 31.861695077992067, "count": 18191, "is_parallel": true, "self": 5.733015899031898, "children": { "_process_rank_one_or_two_observation": { "total": 26.12867917896017, "count": 181910, "is_parallel": true, "self": 26.12867917896017 } } } } } } } } } } }, "trainer_advance": { "total": 118.39108097799294, "count": 18192, "self": 0.4518629689921454, "children": { "process_trajectory": { "total": 25.682380178000017, "count": 18192, "self": 25.244441297000094, "children": { "RLTrainer._checkpoint": { "total": 0.43793888099992273, "count": 4, "self": 0.43793888099992273 } } }, "_update_policy": { "total": 92.25683783100078, "count": 90, "self": 38.30438879400231, "children": { "TorchPPOOptimizer.update": { "total": 53.95244903699847, "count": 4587, "self": 53.95244903699847 } } } } } } }, "trainer_threads": { "total": 9.970001428882824e-07, "count": 1, "self": 9.970001428882824e-07 }, "TrainerController._save_models": { "total": 0.08461994599997524, "count": 1, "self": 0.0008581859999594599, "children": { "RLTrainer._checkpoint": { "total": 0.08376176000001578, "count": 1, "self": 0.08376176000001578 } } } } } } }