{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9739136099815369, "min": 0.9717512726783752, "max": 2.872757911682129, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9256.0751953125, "min": 9256.0751953125, "max": 29325.11328125, "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": 13.078410148620605, "min": 0.12030229717493057, "max": 13.078410148620605, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2550.2900390625, "min": 23.338645935058594, "max": 2660.043212890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07018655113329171, "min": 0.06436740309239694, "max": 0.07659033096256192, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28074620453316684, "min": 0.2664414592379449, "max": 0.36921473560312945, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20647891691210224, "min": 0.14266676286135016, "max": 0.26945396651532133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.825915667648409, "min": 0.5706670514454006, "max": 1.3045475068045598, "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": 25.522727272727273, "min": 3.659090909090909, "max": 25.87272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 161.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.659090909090909, "max": 25.87272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 161.0, "max": 1423.0, "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": "1755668165", "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.yml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1755668605" }, "total": 440.86913596500017, "count": 1, "self": 0.4850282940003581, "children": { "run_training.setup": { "total": 0.02248204599982273, "count": 1, "self": 0.02248204599982273 }, "TrainerController.start_learning": { "total": 440.361625625, "count": 1, "self": 0.42092971602664875, "children": { "TrainerController._reset_env": { "total": 2.272829859000012, "count": 1, "self": 2.272829859000012 }, "TrainerController.advance": { "total": 437.5766476979734, "count": 18192, "self": 0.4056891429784173, "children": { "env_step": { "total": 317.31080361599925, "count": 18192, "self": 244.7089950379941, "children": { "SubprocessEnvManager._take_step": { "total": 72.34924167503004, "count": 18192, "self": 1.3183282560448788, "children": { "TorchPolicy.evaluate": { "total": 71.03091341898516, "count": 18192, "self": 71.03091341898516 } } }, "workers": { "total": 0.2525669029751043, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 438.92621414600126, "count": 18192, "is_parallel": true, "self": 224.44912637000834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001965505000043777, "count": 1, "is_parallel": true, "self": 0.0006461149996539461, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013193900003898307, "count": 10, "is_parallel": true, "self": 0.0013193900003898307 } } }, "UnityEnvironment.step": { "total": 0.07401445100003912, "count": 1, "is_parallel": true, "self": 0.000617044999899008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043907200006287894, "count": 1, "is_parallel": true, "self": 0.00043907200006287894 }, "communicator.exchange": { "total": 0.07101374600006238, "count": 1, "is_parallel": true, "self": 0.07101374600006238 }, "steps_from_proto": { "total": 0.0019445880000148463, "count": 1, "is_parallel": true, "self": 0.0003929420004169515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015516459995978948, "count": 10, "is_parallel": true, "self": 0.0015516459995978948 } } } } } } }, "UnityEnvironment.step": { "total": 214.4770877759929, "count": 18191, "is_parallel": true, "self": 9.932813657995212, "children": { "UnityEnvironment._generate_step_input": { "total": 5.596313014985299, "count": 18191, "is_parallel": true, "self": 5.596313014985299 }, "communicator.exchange": { "total": 166.0382604569902, "count": 18191, "is_parallel": true, "self": 166.0382604569902 }, "steps_from_proto": { "total": 32.9097006460222, "count": 18191, "is_parallel": true, "self": 5.966822388015089, "children": { "_process_rank_one_or_two_observation": { "total": 26.942878258007113, "count": 181910, "is_parallel": true, "self": 26.942878258007113 } } } } } } } } } } }, "trainer_advance": { "total": 119.86015493899572, "count": 18192, "self": 0.5284307429888031, "children": { "process_trajectory": { "total": 26.62389668400624, "count": 18192, "self": 26.26106068400668, "children": { "RLTrainer._checkpoint": { "total": 0.36283599999956095, "count": 4, "self": 0.36283599999956095 } } }, "_update_policy": { "total": 92.70782751200068, "count": 90, "self": 38.61176922000823, "children": { "TorchPPOOptimizer.update": { "total": 54.09605829199245, "count": 4587, "self": 54.09605829199245 } } } } } } }, "trainer_threads": { "total": 9.049999789567664e-07, "count": 1, "self": 9.049999789567664e-07 }, "TrainerController._save_models": { "total": 0.0912174469999627, "count": 1, "self": 0.0008228229999076575, "children": { "RLTrainer._checkpoint": { "total": 0.09039462400005505, "count": 1, "self": 0.09039462400005505 } } } } } } }