{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8725874423980713, "min": 0.8673766255378723, "max": 2.8575589656829834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8293.0712890625, "min": 8293.0712890625, "max": 29169.962890625, "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": 13.397688865661621, "min": 0.3269420266151428, "max": 13.397688865661621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2612.54931640625, "min": 63.426753997802734, "max": 2721.484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07010816141979268, "min": 0.06393034375043286, "max": 0.07383869267762158, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2804326456791707, "min": 0.25932453519978, "max": 0.3644686500349552, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19612823269676927, "min": 0.09890808804102205, "max": 0.29443932134731143, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7845129307870771, "min": 0.3956323521640882, "max": 1.4004139318770052, "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": 26.15909090909091, "min": 2.909090909090909, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1151.0, "min": 128.0, "max": 1472.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.15909090909091, "min": 2.909090909090909, "max": 26.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1151.0, "min": 128.0, "max": 1472.0, "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": "1736549120", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736549546" }, "total": 426.22424097900006, "count": 1, "self": 0.426059309999971, "children": { "run_training.setup": { "total": 0.056605371000046034, "count": 1, "self": 0.056605371000046034 }, "TrainerController.start_learning": { "total": 425.74157629800004, "count": 1, "self": 0.3309269649922726, "children": { "TrainerController._reset_env": { "total": 4.815941296000005, "count": 1, "self": 4.815941296000005 }, "TrainerController.advance": { "total": 420.51233774900766, "count": 18192, "self": 0.3486231700041458, "children": { "env_step": { "total": 296.79993458300544, "count": 18192, "self": 226.25935210299747, "children": { "SubprocessEnvManager._take_step": { "total": 70.32917478400833, "count": 18192, "self": 1.216101977002154, "children": { "TorchPolicy.evaluate": { "total": 69.11307280700618, "count": 18192, "self": 69.11307280700618 } } }, "workers": { "total": 0.2114076959996396, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 424.3923236309941, "count": 18192, "is_parallel": true, "self": 225.856210183989, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002202253000007204, "count": 1, "is_parallel": true, "self": 0.0006379480000191506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015643049999880532, "count": 10, "is_parallel": true, "self": 0.0015643049999880532 } } }, "UnityEnvironment.step": { "total": 0.03500499800003354, "count": 1, "is_parallel": true, "self": 0.0006477330000507209, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003709579999622292, "count": 1, "is_parallel": true, "self": 0.0003709579999622292 }, "communicator.exchange": { "total": 0.032142860000021756, "count": 1, "is_parallel": true, "self": 0.032142860000021756 }, "steps_from_proto": { "total": 0.0018434469999988323, "count": 1, "is_parallel": true, "self": 0.00035918300000048475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014842639999983476, "count": 10, "is_parallel": true, "self": 0.0014842639999983476 } } } } } } }, "UnityEnvironment.step": { "total": 198.5361134470051, "count": 18191, "is_parallel": true, "self": 9.82766690400905, "children": { "UnityEnvironment._generate_step_input": { "total": 5.409320797004, "count": 18191, "is_parallel": true, "self": 5.409320797004 }, "communicator.exchange": { "total": 151.27532174999124, "count": 18191, "is_parallel": true, "self": 151.27532174999124 }, "steps_from_proto": { "total": 32.02380399600082, "count": 18191, "is_parallel": true, "self": 5.708851637007854, "children": { "_process_rank_one_or_two_observation": { "total": 26.31495235899297, "count": 181910, "is_parallel": true, "self": 26.31495235899297 } } } } } } } } } } }, "trainer_advance": { "total": 123.36377999599807, "count": 18192, "self": 0.37864658799958306, "children": { "process_trajectory": { "total": 28.828163790998303, "count": 18192, "self": 28.352984596998226, "children": { "RLTrainer._checkpoint": { "total": 0.47517919400007713, "count": 4, "self": 0.47517919400007713 } } }, "_update_policy": { "total": 94.15696961700019, "count": 90, "self": 38.97721980000267, "children": { "TorchPPOOptimizer.update": { "total": 55.179749816997514, "count": 4587, "self": 55.179749816997514 } } } } } } }, "trainer_threads": { "total": 9.390000741404947e-07, "count": 1, "self": 9.390000741404947e-07 }, "TrainerController._save_models": { "total": 0.08236934900003234, "count": 1, "self": 0.0009327050000820236, "children": { "RLTrainer._checkpoint": { "total": 0.08143664399995032, "count": 1, "self": 0.08143664399995032 } } } } } } }