{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9082087874412537, "min": 0.9060767889022827, "max": 2.8676702976226807, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8631.6162109375, "min": 8631.6162109375, "max": 29273.177734375, "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": 13.24351692199707, "min": 0.28583642840385437, "max": 13.24351692199707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2582.48583984375, "min": 55.452266693115234, "max": 2690.825439453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09316941940778634, "min": 0.09316941940778634, "max": 0.10633131119099619, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.37267767763114534, "min": 0.37267767763114534, "max": 0.531656555954981, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1796282591736492, "min": 0.1099558026328975, "max": 0.28154423504191284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7185130366945968, "min": 0.43982321053159, "max": 1.3127186440807932, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "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": 26.386363636363637, "min": 3.1136363636363638, "max": 26.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1161.0, "min": 137.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.386363636363637, "min": 3.1136363636363638, "max": 26.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1161.0, "min": 137.0, "max": 1428.0, "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": "1779887935", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1779888585" }, "total": 649.9418392939999, "count": 1, "self": 0.5905147009998473, "children": { "run_training.setup": { "total": 0.03183859700016001, "count": 1, "self": 0.03183859700016001 }, "TrainerController.start_learning": { "total": 649.3194859959999, "count": 1, "self": 0.5921733039901937, "children": { "TrainerController._reset_env": { "total": 3.1773203049999665, "count": 1, "self": 3.1773203049999665 }, "TrainerController.advance": { "total": 645.4794628240097, "count": 18192, "self": 0.6732999559849304, "children": { "env_step": { "total": 423.2551363460118, "count": 18192, "self": 367.0260468249762, "children": { "SubprocessEnvManager._take_step": { "total": 55.85102293500995, "count": 18192, "self": 2.050922412998034, "children": { "TorchPolicy.evaluate": { "total": 53.80010052201192, "count": 18192, "self": 53.80010052201192 } } }, "workers": { "total": 0.37806658602562493, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 646.3108106909863, "count": 18192, "is_parallel": true, "self": 328.5624920850023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005516879999959201, "count": 1, "is_parallel": true, "self": 0.003967527999975573, "children": { "_process_rank_one_or_two_observation": { "total": 0.001549351999983628, "count": 10, "is_parallel": true, "self": 0.001549351999983628 } } }, "UnityEnvironment.step": { "total": 0.0428268929999831, "count": 1, "is_parallel": true, "self": 0.000722821999943335, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004796560001523176, "count": 1, "is_parallel": true, "self": 0.0004796560001523176 }, "communicator.exchange": { "total": 0.039400070999818126, "count": 1, "is_parallel": true, "self": 0.039400070999818126 }, "steps_from_proto": { "total": 0.0022243440000693226, "count": 1, "is_parallel": true, "self": 0.0004206309999972291, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018037130000720936, "count": 10, "is_parallel": true, "self": 0.0018037130000720936 } } } } } } }, "UnityEnvironment.step": { "total": 317.74831860598397, "count": 18191, "is_parallel": true, "self": 14.563851238035795, "children": { "UnityEnvironment._generate_step_input": { "total": 7.7084965579754225, "count": 18191, "is_parallel": true, "self": 7.7084965579754225 }, "communicator.exchange": { "total": 246.22839854299673, "count": 18191, "is_parallel": true, "self": 246.22839854299673 }, "steps_from_proto": { "total": 49.24757226697602, "count": 18191, "is_parallel": true, "self": 8.704771586964625, "children": { "_process_rank_one_or_two_observation": { "total": 40.542800680011396, "count": 181910, "is_parallel": true, "self": 40.542800680011396 } } } } } } } } } } }, "trainer_advance": { "total": 221.551026522013, "count": 18192, "self": 0.864402156023516, "children": { "process_trajectory": { "total": 31.15272031799077, "count": 18192, "self": 30.767629106990626, "children": { "RLTrainer._checkpoint": { "total": 0.38509121100014454, "count": 4, "self": 0.38509121100014454 } } }, "_update_policy": { "total": 189.5339040479987, "count": 90, "self": 49.68910326499122, "children": { "TorchPPOOptimizer.update": { "total": 139.84480078300749, "count": 9177, "self": 139.84480078300749 } } } } } } }, "trainer_threads": { "total": 1.032999989547534e-06, "count": 1, "self": 1.032999989547534e-06 }, "TrainerController._save_models": { "total": 0.07052853000004689, "count": 1, "self": 0.0008835759999783477, "children": { "RLTrainer._checkpoint": { "total": 0.06964495400006854, "count": 1, "self": 0.06964495400006854 } } } } } } }