{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9126696586608887, "min": 0.8960018157958984, "max": 2.853381633758545, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8674.0126953125, "min": 8674.0126953125, "max": 29127.3203125, "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": 12.125924110412598, "min": 0.5267843008041382, "max": 12.125924110412598, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2364.55517578125, "min": 102.19615173339844, "max": 2444.84765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07411304535501176, "min": 0.06355830319351334, "max": 0.07411304535501176, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29645218142004703, "min": 0.25572781014089546, "max": 0.35750063873135385, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1635461354664728, "min": 0.13110489015211807, "max": 0.28252471901622467, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6541845418658911, "min": 0.5244195606084723, "max": 1.4126235950811235, "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": 24.136363636363637, "min": 3.727272727272727, "max": 24.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1062.0, "min": 164.0, "max": 1304.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.136363636363637, "min": 3.727272727272727, "max": 24.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1062.0, "min": 164.0, "max": 1304.0, "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": "1767205501", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767205949" }, "total": 448.603592156, "count": 1, "self": 0.4360570229998757, "children": { "run_training.setup": { "total": 0.027712724000025446, "count": 1, "self": 0.027712724000025446 }, "TrainerController.start_learning": { "total": 448.1398224090001, "count": 1, "self": 0.3719750020054562, "children": { "TrainerController._reset_env": { "total": 2.751475680999988, "count": 1, "self": 2.751475680999988 }, "TrainerController.advance": { "total": 444.93239916399455, "count": 18192, "self": 0.387930980994156, "children": { "env_step": { "total": 325.1041480149869, "count": 18192, "self": 254.99952865899547, "children": { "SubprocessEnvManager._take_step": { "total": 69.87833344099602, "count": 18192, "self": 1.284361254997748, "children": { "TorchPolicy.evaluate": { "total": 68.59397218599827, "count": 18192, "self": 68.59397218599827 } } }, "workers": { "total": 0.22628591499540107, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 446.314051194003, "count": 18192, "is_parallel": true, "self": 222.12712239499638, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00542760099995121, "count": 1, "is_parallel": true, "self": 0.003956079999852591, "children": { "_process_rank_one_or_two_observation": { "total": 0.001471521000098619, "count": 10, "is_parallel": true, "self": 0.001471521000098619 } } }, "UnityEnvironment.step": { "total": 0.0360079910000195, "count": 1, "is_parallel": true, "self": 0.000601295000024038, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003729380000550009, "count": 1, "is_parallel": true, "self": 0.0003729380000550009 }, "communicator.exchange": { "total": 0.03303734600001462, "count": 1, "is_parallel": true, "self": 0.03303734600001462 }, "steps_from_proto": { "total": 0.00199641199992584, "count": 1, "is_parallel": true, "self": 0.0004322809999166566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015641310000091835, "count": 10, "is_parallel": true, "self": 0.0015641310000091835 } } } } } } }, "UnityEnvironment.step": { "total": 224.18692879900664, "count": 18191, "is_parallel": true, "self": 10.556137834988249, "children": { "UnityEnvironment._generate_step_input": { "total": 5.574019341001986, "count": 18191, "is_parallel": true, "self": 5.574019341001986 }, "communicator.exchange": { "total": 170.53258646900792, "count": 18191, "is_parallel": true, "self": 170.53258646900792 }, "steps_from_proto": { "total": 37.52418515400848, "count": 18191, "is_parallel": true, "self": 6.685080113007871, "children": { "_process_rank_one_or_two_observation": { "total": 30.839105041000607, "count": 181910, "is_parallel": true, "self": 30.839105041000607 } } } } } } } } } } }, "trainer_advance": { "total": 119.4403201680135, "count": 18192, "self": 0.4698500999979842, "children": { "process_trajectory": { "total": 26.943939716015734, "count": 18192, "self": 26.372417631015765, "children": { "RLTrainer._checkpoint": { "total": 0.5715220849999696, "count": 4, "self": 0.5715220849999696 } } }, "_update_policy": { "total": 92.02653035199978, "count": 90, "self": 37.76082644699795, "children": { "TorchPPOOptimizer.update": { "total": 54.26570390500183, "count": 4587, "self": 54.26570390500183 } } } } } } }, "trainer_threads": { "total": 9.76000137598021e-07, "count": 1, "self": 9.76000137598021e-07 }, "TrainerController._save_models": { "total": 0.08397158599996146, "count": 1, "self": 0.0008083530001385952, "children": { "RLTrainer._checkpoint": { "total": 0.08316323299982287, "count": 1, "self": 0.08316323299982287 } } } } } } }