{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.283064603805542, "min": 1.283064603805542, "max": 2.8894717693328857, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5716.052734375, "min": 5716.052734375, "max": 19197.650390625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 249880.0, "min": 4912.0, "max": 249880.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 249880.0, "min": 4912.0, "max": 249880.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 24.551767349243164, "min": 0.02715410105884075, "max": 24.551767349243164, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1178.48486328125, "min": 1.3033968210220337, "max": 1228.746826171875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 4378.0, "min": 4378.0, "max": 6567.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.272727272727273, "min": 2.6818181818181817, "max": 26.51851851851852, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 578.0, "min": 59.0, "max": 779.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 2.6818181818181817, "max": 26.51851851851852, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 578.0, "min": 59.0, "max": 779.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.050374415147063485, "min": 0.03606104990193511, "max": 0.05759636968209901, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.050374415147063485, "min": 0.03606104990193511, "max": 0.10187350098614628, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1911360056961284, "min": 0.09473218321800232, "max": 0.3654931355925167, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1911360056961284, "min": 0.09473218321800232, "max": 0.6713911156443988, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00010144004927999997, "min": 0.00010144004927999997, "max": 0.00019824000088, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00010144004927999997, "min": 0.00010144004927999997, "max": 0.00037008001496, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.15071999999999997, "min": 0.15071999999999997, "max": 0.19912, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.15071999999999997, "min": 0.15071999999999997, "max": 0.38504000000000005, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.002540928, "min": 0.002540928, "max": 0.004956088000000001, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.002540928, "min": 0.002540928, "max": 0.009253496000000002, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727023442", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727024172" }, "total": 729.994286358, "count": 1, "self": 0.010999842999922294, "children": { "run_training.setup": { "total": 0.05049896100001661, "count": 1, "self": 0.05049896100001661 }, "TrainerController.start_learning": { "total": 729.932787554, "count": 1, "self": 1.7766083020130736, "children": { "TrainerController._reset_env": { "total": 2.0671965389999514, "count": 1, "self": 2.0671965389999514 }, "TrainerController.advance": { "total": 725.889319640987, "count": 22945, "self": 0.39339196298783463, "children": { "env_step": { "total": 725.4959276779991, "count": 22945, "self": 570.5068757080278, "children": { "SubprocessEnvManager._take_step": { "total": 154.62392303297833, "count": 22945, "self": 1.9456735979693462, "children": { "TorchPolicy.evaluate": { "total": 152.67824943500898, "count": 22945, "self": 152.67824943500898 } } }, "workers": { "total": 0.36512893699301685, "count": 22944, "self": 0.0, "children": { "worker_root": { "total": 727.3554420830012, "count": 22944, "is_parallel": true, "self": 451.258439566992, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002133714000024156, "count": 1, "is_parallel": true, "self": 0.0006227190000913652, "children": { "_process_rank_one_or_two_observation": { "total": 0.001510994999932791, "count": 10, "is_parallel": true, "self": 0.001510994999932791 } } }, "UnityEnvironment.step": { "total": 0.03648735100000522, "count": 1, "is_parallel": true, "self": 0.0006408929999679458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040243900002678856, "count": 1, "is_parallel": true, "self": 0.00040243900002678856 }, "communicator.exchange": { "total": 0.032155583000019305, "count": 1, "is_parallel": true, "self": 0.032155583000019305 }, "steps_from_proto": { "total": 0.0032884359999911794, "count": 1, "is_parallel": true, "self": 0.00042584900006659154, "children": { "_process_rank_one_or_two_observation": { "total": 0.002862586999924588, "count": 10, "is_parallel": true, "self": 0.002862586999924588 } } } } } } }, "UnityEnvironment.step": { "total": 276.0970025160092, "count": 22943, "is_parallel": true, "self": 12.622228944000028, "children": { "UnityEnvironment._generate_step_input": { "total": 6.639933890009161, "count": 22943, "is_parallel": true, "self": 6.639933890009161 }, "communicator.exchange": { "total": 216.36968423000405, "count": 22943, "is_parallel": true, "self": 216.36968423000405 }, "steps_from_proto": { "total": 40.46515545199594, "count": 22943, "is_parallel": true, "self": 7.693580631968018, "children": { "_process_rank_one_or_two_observation": { "total": 32.77157482002792, "count": 229430, "is_parallel": true, "self": 32.77157482002792 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.491400017694104e-05, "count": 1, "self": 6.491400017694104e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 718.2388507330124, "count": 537962, "is_parallel": true, "self": 10.010347316031357, "children": { "process_trajectory": { "total": 246.09446945398065, "count": 537963, "is_parallel": true, "self": 243.2749854109809, "children": { "RLTrainer._checkpoint": { "total": 2.819484042999761, "count": 10, "is_parallel": true, "self": 2.819484042999761 } } }, "_update_policy": { "total": 462.1340339630005, "count": 56, "is_parallel": true, "self": 96.58517024600252, "children": { "TorchPPOOptimizer.update": { "total": 365.54886371699797, "count": 4785, "is_parallel": true, "self": 365.54886371699797 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19959815799984426, "count": 1, "self": 0.004359148999810714, "children": { "RLTrainer._checkpoint": { "total": 0.19523900900003355, "count": 1, "self": 0.19523900900003355 } } } } } } }