{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9635018110275269, "min": 0.9635018110275269, "max": 2.877673864364624, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9263.1064453125, "min": 9263.1064453125, "max": 29470.2578125, "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": 12.769116401672363, "min": 0.46849191188812256, "max": 12.769116401672363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2489.977783203125, "min": 90.8874282836914, "max": 2591.79052734375, "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": 0.06726945656694572, "min": 0.06348469743388704, "max": 0.07414997835976286, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26907782626778287, "min": 0.26093915429915865, "max": 0.37074989179881435, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19459565118521305, "min": 0.09924142693247026, "max": 0.2955612395323959, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7783826047408522, "min": 0.39696570772988105, "max": 1.4778061976619794, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.106097298000005e-06, "min": 8.106097298000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.242438919200002e-05, "min": 3.242438919200002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10270200000000002, "min": 0.10270200000000002, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41080800000000006, "min": 0.41080800000000006, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014482980000000007, "min": 0.00014482980000000007, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005793192000000003, "min": 0.0005793192000000003, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.75, "min": 3.0454545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 134.0, "max": 1384.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.0454545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 134.0, "max": 1384.0, "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": "1719539885", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719540497" }, "total": 612.122156966, "count": 1, "self": 0.594032832000039, "children": { "run_training.setup": { "total": 0.10714840200000708, "count": 1, "self": 0.10714840200000708 }, "TrainerController.start_learning": { "total": 611.420975732, "count": 1, "self": 0.8270345879999468, "children": { "TrainerController._reset_env": { "total": 3.3395371649999674, "count": 1, "self": 3.3395371649999674 }, "TrainerController.advance": { "total": 607.1489578790001, "count": 18208, "self": 0.4235819480036298, "children": { "env_step": { "total": 606.7253759309965, "count": 18208, "self": 469.67418223499277, "children": { "SubprocessEnvManager._take_step": { "total": 136.6329459199958, "count": 18208, "self": 2.928377985998111, "children": { "TorchPolicy.evaluate": { "total": 133.70456793399768, "count": 18208, "self": 133.70456793399768 } } }, "workers": { "total": 0.41824777600794505, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 609.3407353679975, "count": 18208, "is_parallel": true, "self": 287.2187176809889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006048167999949783, "count": 1, "is_parallel": true, "self": 0.004199648000110301, "children": { "_process_rank_one_or_two_observation": { "total": 0.001848519999839482, "count": 10, "is_parallel": true, "self": 0.001848519999839482 } } }, "UnityEnvironment.step": { "total": 0.043740603000003375, "count": 1, "is_parallel": true, "self": 0.0009515990000181773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004472339999779251, "count": 1, "is_parallel": true, "self": 0.0004472339999779251 }, "communicator.exchange": { "total": 0.0398361040000168, "count": 1, "is_parallel": true, "self": 0.0398361040000168 }, "steps_from_proto": { "total": 0.0025056659999904696, "count": 1, "is_parallel": true, "self": 0.0005013279999275255, "children": { "_process_rank_one_or_two_observation": { "total": 0.002004338000062944, "count": 10, "is_parallel": true, "self": 0.002004338000062944 } } } } } } }, "UnityEnvironment.step": { "total": 322.12201768700857, "count": 18207, "is_parallel": true, "self": 15.305588772007582, "children": { "UnityEnvironment._generate_step_input": { "total": 7.590577485005042, "count": 18207, "is_parallel": true, "self": 7.590577485005042 }, "communicator.exchange": { "total": 254.32421824999653, "count": 18207, "is_parallel": true, "self": 254.32421824999653 }, "steps_from_proto": { "total": 44.90163317999941, "count": 18207, "is_parallel": true, "self": 8.812011751965201, "children": { "_process_rank_one_or_two_observation": { "total": 36.08962142803421, "count": 182070, "is_parallel": true, "self": 36.08962142803421 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017331599997305602, "count": 1, "self": 0.00017331599997305602, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 600.1874991019635, "count": 777112, "is_parallel": true, "self": 17.954540593975366, "children": { "process_trajectory": { "total": 326.5552699219882, "count": 777112, "is_parallel": true, "self": 325.52944598798825, "children": { "RLTrainer._checkpoint": { "total": 1.025823933999959, "count": 4, "is_parallel": true, "self": 1.025823933999959 } } }, "_update_policy": { "total": 255.67768858599993, "count": 90, "is_parallel": true, "self": 71.34484258800404, "children": { "TorchPPOOptimizer.update": { "total": 184.3328459979959, "count": 4584, "is_parallel": true, "self": 184.3328459979959 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1052727840000216, "count": 1, "self": 0.0012353250000387561, "children": { "RLTrainer._checkpoint": { "total": 0.10403745899998285, "count": 1, "self": 0.10403745899998285 } } } } } } }