{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7273720502853394, "min": 0.7273720502853394, "max": 2.7979791164398193, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14401.966796875, "min": 14401.966796875, "max": 57369.76171875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.030179023742676, "min": 1.1284499168395996, "max": 13.030179023742676, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5199.04150390625, "min": 450.25152587890625, "max": 5199.04150390625, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06388534142720474, "min": 0.06388534142720474, "max": 0.07315084368319197, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.5749680728448426, "min": 0.5749680728448426, "max": 0.6583575931487277, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18471286328984243, "min": 0.17604525040374552, "max": 0.2716292394142525, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.662415769608582, "min": 1.5844072536337097, "max": 2.4446631547282722, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.1776094556000006e-05, "min": 2.1776094556000006e-05, "max": 0.00037817600545600005, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00019598485100400006, "min": 0.00019598485100400006, "max": 0.0034035840491040007, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10544400000000001, "min": 0.10544400000000001, "max": 0.19454400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9489960000000001, "min": 0.9489960000000001, "max": 1.7508960000000002, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00028165560000000005, "min": 0.00028165560000000005, "max": 0.0047277456, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0025349004000000007, "min": 0.0025349004000000007, "max": 0.0425497104, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 19701.0, "min": 19701.0, "max": 19701.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.7979797979798, "min": 5.404040404040404, "max": 25.7979797979798, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 2554.0, "min": 535.0, "max": 2554.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.7979797979798, "min": 5.404040404040404, "max": 25.7979797979798, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 2554.0, "min": 535.0, "max": 2554.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748414469", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748414882" }, "total": 413.2558686599998, "count": 1, "self": 0.4438873199997033, "children": { "run_training.setup": { "total": 0.02965529800007971, "count": 1, "self": 0.02965529800007971 }, "TrainerController.start_learning": { "total": 412.782326042, "count": 1, "self": 0.3389531480002006, "children": { "TrainerController._reset_env": { "total": 3.6728264000000763, "count": 1, "self": 3.6728264000000763 }, "TrainerController.advance": { "total": 408.68416498199986, "count": 18192, "self": 0.35618187599243356, "children": { "env_step": { "total": 288.81044256702353, "count": 18192, "self": 220.44717880906705, "children": { "SubprocessEnvManager._take_step": { "total": 68.16555426698369, "count": 18192, "self": 1.2206363869941015, "children": { "TorchPolicy.evaluate": { "total": 66.94491787998959, "count": 18192, "self": 66.94491787998959 } } }, "workers": { "total": 0.1977094909727839, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 411.39937476199066, "count": 18192, "is_parallel": true, "self": 217.85587383799952, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004912291000209734, "count": 1, "is_parallel": true, "self": 0.003551191000497056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013610999997126783, "count": 10, "is_parallel": true, "self": 0.0013610999997126783 } } }, "UnityEnvironment.step": { "total": 0.0359621679999691, "count": 1, "is_parallel": true, "self": 0.0005905769999117183, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039945400021679234, "count": 1, "is_parallel": true, "self": 0.00039945400021679234 }, "communicator.exchange": { "total": 0.03312588199992206, "count": 1, "is_parallel": true, "self": 0.03312588199992206 }, "steps_from_proto": { "total": 0.0018462549999185285, "count": 1, "is_parallel": true, "self": 0.00040436900007989607, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014418859998386324, "count": 10, "is_parallel": true, "self": 0.0014418859998386324 } } } } } } }, "UnityEnvironment.step": { "total": 193.54350092399113, "count": 18191, "is_parallel": true, "self": 9.468067610971957, "children": { "UnityEnvironment._generate_step_input": { "total": 5.325981763001437, "count": 18191, "is_parallel": true, "self": 5.325981763001437 }, "communicator.exchange": { "total": 148.70434467798532, "count": 18191, "is_parallel": true, "self": 148.70434467798532 }, "steps_from_proto": { "total": 30.04510687203242, "count": 18191, "is_parallel": true, "self": 5.323646552033551, "children": { "_process_rank_one_or_two_observation": { "total": 24.72146031999887, "count": 181910, "is_parallel": true, "self": 24.72146031999887 } } } } } } } } } } }, "trainer_advance": { "total": 119.5175405389839, "count": 18192, "self": 0.40123433497160477, "children": { "process_trajectory": { "total": 26.37485031001256, "count": 18192, "self": 25.970361752012877, "children": { "RLTrainer._checkpoint": { "total": 0.4044885579996844, "count": 4, "self": 0.4044885579996844 } } }, "_update_policy": { "total": 92.74145589399973, "count": 90, "self": 37.29387848200781, "children": { "TorchPPOOptimizer.update": { "total": 55.447577411991915, "count": 4587, "self": 55.447577411991915 } } } } } } }, "trainer_threads": { "total": 1.0700000530050602e-06, "count": 1, "self": 1.0700000530050602e-06 }, "TrainerController._save_models": { "total": 0.08638044199983597, "count": 1, "self": 0.000837871999692652, "children": { "RLTrainer._checkpoint": { "total": 0.08554257000014331, "count": 1, "self": 0.08554257000014331 } } } } } } }