{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7225422859191895, "min": 0.7215284109115601, "max": 2.8647565841674805, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6867.0419921875, "min": 6867.0419921875, "max": 29243.435546875, "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": 13.159317016601562, "min": 0.3091595768928528, "max": 13.212692260742188, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2566.06689453125, "min": 59.97695541381836, "max": 2695.38916015625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07011852274059921, "min": 0.06247278762269108, "max": 0.072216766043151, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28047409096239684, "min": 0.2564693737110835, "max": 0.3596245448490806, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19871438776745518, "min": 0.1038654672447592, "max": 0.28327260379697766, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7948575510698207, "min": 0.4154618689790368, "max": 1.4163630189848884, "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": 26.34090909090909, "min": 3.409090909090909, "max": 26.34090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1159.0, "min": 150.0, "max": 1429.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.34090909090909, "min": 3.409090909090909, "max": 26.34090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1159.0, "min": 150.0, "max": 1429.0, "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": "1741745806", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741746288" }, "total": 482.42199941599995, "count": 1, "self": 0.43856998899991595, "children": { "run_training.setup": { "total": 0.024325499000042328, "count": 1, "self": 0.024325499000042328 }, "TrainerController.start_learning": { "total": 481.959103928, "count": 1, "self": 0.5063108529964211, "children": { "TrainerController._reset_env": { "total": 3.0701913159999776, "count": 1, "self": 3.0701913159999776 }, "TrainerController.advance": { "total": 478.2823858350034, "count": 18192, "self": 0.508052989965222, "children": { "env_step": { "total": 346.48695998002165, "count": 18192, "self": 262.7109865230195, "children": { "SubprocessEnvManager._take_step": { "total": 83.48546252300957, "count": 18192, "self": 1.491984040006514, "children": { "TorchPolicy.evaluate": { "total": 81.99347848300306, "count": 18192, "self": 81.99347848300306 } } }, "workers": { "total": 0.29051093399255024, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 480.0459820479957, "count": 18192, "is_parallel": true, "self": 251.6978975229997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005269371999929717, "count": 1, "is_parallel": true, "self": 0.003771697000047425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014976749998822925, "count": 10, "is_parallel": true, "self": 0.0014976749998822925 } } }, "UnityEnvironment.step": { "total": 0.04051575599999069, "count": 1, "is_parallel": true, "self": 0.0005957060000127967, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004290879999189201, "count": 1, "is_parallel": true, "self": 0.0004290879999189201 }, "communicator.exchange": { "total": 0.03757215300004191, "count": 1, "is_parallel": true, "self": 0.03757215300004191 }, "steps_from_proto": { "total": 0.0019188090000170632, "count": 1, "is_parallel": true, "self": 0.00040161199990507157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015171970001119917, "count": 10, "is_parallel": true, "self": 0.0015171970001119917 } } } } } } }, "UnityEnvironment.step": { "total": 228.348084524996, "count": 18191, "is_parallel": true, "self": 10.438613544005534, "children": { "UnityEnvironment._generate_step_input": { "total": 6.223997641988376, "count": 18191, "is_parallel": true, "self": 6.223997641988376 }, "communicator.exchange": { "total": 176.67635322700846, "count": 18191, "is_parallel": true, "self": 176.67635322700846 }, "steps_from_proto": { "total": 35.00912011199364, "count": 18191, "is_parallel": true, "self": 6.678246393958489, "children": { "_process_rank_one_or_two_observation": { "total": 28.33087371803515, "count": 181910, "is_parallel": true, "self": 28.33087371803515 } } } } } } } } } } }, "trainer_advance": { "total": 131.28737286501655, "count": 18192, "self": 0.6561685790211413, "children": { "process_trajectory": { "total": 29.54572134299508, "count": 18192, "self": 28.799368080995123, "children": { "RLTrainer._checkpoint": { "total": 0.7463532619999569, "count": 4, "self": 0.7463532619999569 } } }, "_update_policy": { "total": 101.08548294300033, "count": 90, "self": 40.0753468360017, "children": { "TorchPPOOptimizer.update": { "total": 61.01013610699863, "count": 4587, "self": 61.01013610699863 } } } } } } }, "trainer_threads": { "total": 1.050000037139398e-06, "count": 1, "self": 1.050000037139398e-06 }, "TrainerController._save_models": { "total": 0.1002148740001303, "count": 1, "self": 0.0012512210000750201, "children": { "RLTrainer._checkpoint": { "total": 0.09896365300005527, "count": 1, "self": 0.09896365300005527 } } } } } } }