{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7375858426094055, "min": 0.711052417755127, "max": 2.850282907485962, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7010.015625, "min": 7010.015625, "max": 29095.6875, "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": 11.968770027160645, "min": 0.4280170500278473, "max": 12.05224895477295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2333.91015625, "min": 83.03530883789062, "max": 2458.65869140625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07436658814394297, "min": 0.06221517412033041, "max": 0.07487450886709505, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29746635257577186, "min": 0.24886069648132164, "max": 0.3743725443354753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19503077492117882, "min": 0.13418307909102856, "max": 0.271198314778945, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7801230996847153, "min": 0.5367323163641142, "max": 1.310492550333341, "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": 22.818181818181817, "min": 3.840909090909091, "max": 23.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1004.0, "min": 169.0, "max": 1312.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.818181818181817, "min": 3.840909090909091, "max": 23.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1004.0, "min": 169.0, "max": 1312.0, "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": "1782156792", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/env/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": "1782157264" }, "total": 471.918281104, "count": 1, "self": 0.48624797399952513, "children": { "run_training.setup": { "total": 0.021355888000471168, "count": 1, "self": 0.021355888000471168 }, "TrainerController.start_learning": { "total": 471.410677242, "count": 1, "self": 0.3852805781416464, "children": { "TrainerController._reset_env": { "total": 5.81953385900033, "count": 1, "self": 5.81953385900033 }, "TrainerController.advance": { "total": 465.1223640938588, "count": 18192, "self": 0.3862588929641788, "children": { "env_step": { "total": 341.4201872088843, "count": 18192, "self": 267.26388914198924, "children": { "SubprocessEnvManager._take_step": { "total": 73.9334171799328, "count": 18192, "self": 1.323856148888808, "children": { "TorchPolicy.evaluate": { "total": 72.609561031044, "count": 18192, "self": 72.609561031044 } } }, "workers": { "total": 0.22288088696222985, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 469.5080155920896, "count": 18192, "is_parallel": true, "self": 234.46080210507444, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004180638000434556, "count": 1, "is_parallel": true, "self": 0.0027812500011350494, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013993879992995062, "count": 10, "is_parallel": true, "self": 0.0013993879992995062 } } }, "UnityEnvironment.step": { "total": 0.03623657699972682, "count": 1, "is_parallel": true, "self": 0.0006250179994822247, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004497760000958806, "count": 1, "is_parallel": true, "self": 0.0004497760000958806 }, "communicator.exchange": { "total": 0.03329009900062374, "count": 1, "is_parallel": true, "self": 0.03329009900062374 }, "steps_from_proto": { "total": 0.0018716839995249757, "count": 1, "is_parallel": true, "self": 0.00040705800074647414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014646259987785015, "count": 10, "is_parallel": true, "self": 0.0014646259987785015 } } } } } } }, "UnityEnvironment.step": { "total": 235.04721348701514, "count": 18191, "is_parallel": true, "self": 10.42111315715465, "children": { "UnityEnvironment._generate_step_input": { "total": 5.622289222942527, "count": 18191, "is_parallel": true, "self": 5.622289222942527 }, "communicator.exchange": { "total": 179.01953587489606, "count": 18191, "is_parallel": true, "self": 179.01953587489606 }, "steps_from_proto": { "total": 39.9842752320219, "count": 18191, "is_parallel": true, "self": 7.0549127828107885, "children": { "_process_rank_one_or_two_observation": { "total": 32.92936244921111, "count": 181910, "is_parallel": true, "self": 32.92936244921111 } } } } } } } } } } }, "trainer_advance": { "total": 123.31591799201033, "count": 18192, "self": 0.47366348710329476, "children": { "process_trajectory": { "total": 25.227980882907104, "count": 18192, "self": 24.763838167906215, "children": { "RLTrainer._checkpoint": { "total": 0.46414271500088944, "count": 4, "self": 0.46414271500088944 } } }, "_update_policy": { "total": 97.61427362199993, "count": 90, "self": 40.046550323029805, "children": { "TorchPPOOptimizer.update": { "total": 57.56772329897012, "count": 4587, "self": 57.56772329897012 } } } } } } }, "trainer_threads": { "total": 1.0129997463081963e-06, "count": 1, "self": 1.0129997463081963e-06 }, "TrainerController._save_models": { "total": 0.083497697999519, "count": 1, "self": 0.0007109689995559165, "children": { "RLTrainer._checkpoint": { "total": 0.08278672899996309, "count": 1, "self": 0.08278672899996309 } } } } } } }