{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8086255788803101, "min": 0.8086255788803101, "max": 2.8714637756347656, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7685.177734375, "min": 7685.177734375, "max": 29311.90234375, "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": 12.879521369934082, "min": 0.27850791811943054, "max": 12.879521369934082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.506591796875, "min": 54.03053665161133, "max": 2600.13671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07005689349606138, "min": 0.05954070066597755, "max": 0.07671463076600477, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2802275739842455, "min": 0.2492722101903614, "max": 0.3835731538300238, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17584277185447073, "min": 0.1051405752260311, "max": 0.2950157156177596, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7033710874178829, "min": 0.4205623009041244, "max": 1.4750785780887978, "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": 26.068181818181817, "min": 2.727272727272727, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 120.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 2.727272727272727, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 120.0, "max": 1390.0, "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": "1777829372", "python_version": "3.10.19 (main, May 3 2026, 16:56:55) [GCC 15.2.1 20260209]", "command_line_arguments": "/home/lyra/.venvs/mlagents-env/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": "1777829524" }, "total": 151.8789513510128, "count": 1, "self": 0.1667256810469553, "children": { "run_training.setup": { "total": 0.015908729983493686, "count": 1, "self": 0.015908729983493686 }, "TrainerController.start_learning": { "total": 151.69631693998235, "count": 1, "self": 0.1318587043788284, "children": { "TrainerController._reset_env": { "total": 1.4302653789927717, "count": 1, "self": 1.4302653789927717 }, "TrainerController.advance": { "total": 150.1021455116279, "count": 18192, "self": 0.1325040278607048, "children": { "env_step": { "total": 100.57960571179865, "count": 18192, "self": 76.6445588224451, "children": { "SubprocessEnvManager._take_step": { "total": 23.84666412405204, "count": 18192, "self": 0.4761584436346311, "children": { "TorchPolicy.evaluate": { "total": 23.37050568041741, "count": 18192, "self": 23.37050568041741 } } }, "workers": { "total": 0.08838276530150324, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 151.40444063974428, "count": 18192, "is_parallel": true, "self": 84.11320850584889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010607229778543115, "count": 1, "is_parallel": true, "self": 0.00029840294155292213, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007623200363013893, "count": 10, "is_parallel": true, "self": 0.0007623200363013893 } } }, "UnityEnvironment.step": { "total": 0.013050784007646143, "count": 1, "is_parallel": true, "self": 0.0001986259885597974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001574869966134429, "count": 1, "is_parallel": true, "self": 0.0001574869966134429 }, "communicator.exchange": { "total": 0.012099090003175661, "count": 1, "is_parallel": true, "self": 0.012099090003175661 }, "steps_from_proto": { "total": 0.0005955810192972422, "count": 1, "is_parallel": true, "self": 0.00013237801613286138, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004632030031643808, "count": 10, "is_parallel": true, "self": 0.0004632030031643808 } } } } } } }, "UnityEnvironment.step": { "total": 67.29123213389539, "count": 18191, "is_parallel": true, "self": 2.724004420975689, "children": { "UnityEnvironment._generate_step_input": { "total": 1.4187349004496355, "count": 18191, "is_parallel": true, "self": 1.4187349004496355 }, "communicator.exchange": { "total": 55.0043229998555, "count": 18191, "is_parallel": true, "self": 55.0043229998555 }, "steps_from_proto": { "total": 8.144169812614564, "count": 18191, "is_parallel": true, "self": 1.5776092803571373, "children": { "_process_rank_one_or_two_observation": { "total": 6.5665605322574265, "count": 181910, "is_parallel": true, "self": 6.5665605322574265 } } } } } } } } } } }, "trainer_advance": { "total": 49.39003577196854, "count": 18192, "self": 0.16155423279269598, "children": { "process_trajectory": { "total": 10.992303899169201, "count": 18192, "self": 10.839059944148175, "children": { "RLTrainer._checkpoint": { "total": 0.1532439550210256, "count": 4, "self": 0.1532439550210256 } } }, "_update_policy": { "total": 38.236177640006645, "count": 90, "self": 17.928790719859535, "children": { "TorchPPOOptimizer.update": { "total": 20.30738692014711, "count": 4587, "self": 20.30738692014711 } } } } } } }, "trainer_threads": { "total": 4.899920895695686e-07, "count": 1, "self": 4.899920895695686e-07 }, "TrainerController._save_models": { "total": 0.032046854990767315, "count": 1, "self": 0.0004314649850130081, "children": { "RLTrainer._checkpoint": { "total": 0.03161539000575431, "count": 1, "self": 0.03161539000575431 } } } } } } }