{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.602304458618164, "min": 1.602304458618164, "max": 2.8853836059570312, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15475.056640625, "min": 15475.056640625, "max": 29549.212890625, "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": 1.462786078453064, "min": 0.20903053879737854, "max": 1.462786078453064, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 285.2432861328125, "min": 40.55192565917969, "max": 295.2460021972656, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04278062743071046, "min": 0.03740328233245583, "max": 0.05381372995640656, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2994643920149732, "min": 0.25109103050393367, "max": 0.3492709052506447, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.064781530272393, "min": 0.0370886461454488, "max": 0.09625423115988573, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.45347071190675103, "min": 0.2596205230181416, "max": 0.5775253869593143, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.382829907157725e-05, "min": 8.382829907157725e-05, "max": 0.0032732852856490837, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0005867980935010407, "min": 0.0005867980935010407, "max": 0.021797750579737155, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.09912168332660047, "min": 0.06570389216053214, "max": 0.09912168332660047, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6938517832862033, "min": 0.3942233529631929, "max": 0.6938517832862033, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011226110353096256, "min": 0.0011226110353096256, "max": 0.04345472694873276, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.007858277247167379, "min": 0.007858277247167379, "max": 0.2893809637295982, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.386363636363637, "min": 3.022727272727273, "max": 24.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1073.0, "min": 133.0, "max": 1335.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.882754775610838, "min": 2.3405465077270162, "max": 18.882754775610838, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 830.8412101268768, "min": 102.98404633998871, "max": 1033.712035536766, "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": "1734712356", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget14 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734712934" }, "total": 578.3493716190005, "count": 1, "self": 1.054238938000708, "children": { "run_training.setup": { "total": 0.0741157310003473, "count": 1, "self": 0.0741157310003473 }, "TrainerController.start_learning": { "total": 577.2210169499995, "count": 1, "self": 1.023016461919724, "children": { "TrainerController._reset_env": { "total": 3.221277755000301, "count": 1, "self": 3.221277755000301 }, "TrainerController.advance": { "total": 572.8177740130795, "count": 18215, "self": 0.4886110569404991, "children": { "env_step": { "total": 572.329162956139, "count": 18215, "self": 412.958888128067, "children": { "SubprocessEnvManager._take_step": { "total": 158.93467012807014, "count": 18215, "self": 3.019371363108803, "children": { "TorchPolicy.evaluate": { "total": 155.91529876496134, "count": 18215, "self": 155.91529876496134 } } }, "workers": { "total": 0.43560470000193163, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 574.958547064989, "count": 18215, "is_parallel": true, "self": 249.5135799089685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003545269999449374, "count": 1, "is_parallel": true, "self": 0.0008927559983931133, "children": { "_process_rank_one_or_two_observation": { "total": 0.002652514001056261, "count": 10, "is_parallel": true, "self": 0.002652514001056261 } } }, "UnityEnvironment.step": { "total": 0.1095645350005725, "count": 1, "is_parallel": true, "self": 0.0008891070010577096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045683400003326824, "count": 1, "is_parallel": true, "self": 0.00045683400003326824 }, "communicator.exchange": { "total": 0.10594400099944323, "count": 1, "is_parallel": true, "self": 0.10594400099944323 }, "steps_from_proto": { "total": 0.002274593000038294, "count": 1, "is_parallel": true, "self": 0.0004177509981673211, "children": { "_process_rank_one_or_two_observation": { "total": 0.001856842001870973, "count": 10, "is_parallel": true, "self": 0.001856842001870973 } } } } } } }, "UnityEnvironment.step": { "total": 325.44496715602054, "count": 18214, "is_parallel": true, "self": 15.366280455989, "children": { "UnityEnvironment._generate_step_input": { "total": 7.844114936006918, "count": 18214, "is_parallel": true, "self": 7.844114936006918 }, "communicator.exchange": { "total": 255.65704095400451, "count": 18214, "is_parallel": true, "self": 255.65704095400451 }, "steps_from_proto": { "total": 46.57753081002011, "count": 18214, "is_parallel": true, "self": 9.352727159182905, "children": { "_process_rank_one_or_two_observation": { "total": 37.2248036508372, "count": 182140, "is_parallel": true, "self": 37.2248036508372 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003579949998311349, "count": 1, "self": 0.0003579949998311349, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 568.5701288763703, "count": 516846, "is_parallel": true, "self": 12.44683584858194, "children": { "process_trajectory": { "total": 251.86072053578755, "count": 516846, "is_parallel": true, "self": 250.94444069578822, "children": { "RLTrainer._checkpoint": { "total": 0.9162798399993335, "count": 4, "is_parallel": true, "self": 0.9162798399993335 } } }, "_update_policy": { "total": 304.2625724920008, "count": 137, "is_parallel": true, "self": 84.32923142198342, "children": { "TorchPPOOptimizer.update": { "total": 219.93334107001738, "count": 2046, "is_parallel": true, "self": 219.93334107001738 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15859072500006732, "count": 1, "self": 0.0022051480000300216, "children": { "RLTrainer._checkpoint": { "total": 0.1563855770000373, "count": 1, "self": 0.1563855770000373 } } } } } } }