{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8801817893981934, "min": 2.8801817893981934, "max": 2.8801817893981934, "count": 1 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29495.94140625, "min": 29495.94140625, "max": 29495.94140625, "count": 1 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49050334095954895, "min": 0.49050334095954895, "max": 0.49050334095954895, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 95.15764617919922, "min": 95.15764617919922, "max": 95.15764617919922, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 8756.0, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07404546684276783, "min": 0.07404546684276783, "max": 0.07404546684276783, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29618186737107133, "min": 0.29618186737107133, "max": 0.29618186737107133, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10099118845719916, "min": 0.10099118845719916, "max": 0.10099118845719916, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.40396475382879665, "min": 0.40396475382879665, "max": 0.40396475382879665, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00013764005412, "min": 0.00013764005412, "max": 0.00013764005412, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00055056021648, "min": 0.00055056021648, "max": 0.00055056021648, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.14588, "min": 0.14588, "max": 0.14588, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.58352, "min": 0.58352, "max": 0.58352, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.002299412, "min": 0.002299412, "max": 0.002299412, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.009197648, "min": 0.009197648, "max": 0.009197648, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 2.8863636363636362, "min": 2.8863636363636362, "max": 2.8863636363636362, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 127.0, "min": 127.0, "max": 127.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 2.8863636363636362, "min": 2.8863636363636362, "max": 2.8863636363636362, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 127.0, "min": 127.0, "max": 127.0, "count": 1 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714813148", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714813174" }, "total": 25.815106173999993, "count": 1, "self": 0.7448074260000794, "children": { "run_training.setup": { "total": 0.05302846900008262, "count": 1, "self": 0.05302846900008262 }, "TrainerController.start_learning": { "total": 25.01727027899983, "count": 1, "self": 0.049328362005098825, "children": { "TrainerController._reset_env": { "total": 2.742897456000037, "count": 1, "self": 2.742897456000037 }, "TrainerController.advance": { "total": 22.10123112699489, "count": 932, "self": 0.013189132992692976, "children": { "env_step": { "total": 22.088041994002197, "count": 932, "self": 13.504690167004128, "children": { "SubprocessEnvManager._take_step": { "total": 8.569482182999991, "count": 932, "self": 0.07452847099898463, "children": { "TorchPolicy.evaluate": { "total": 8.494953712001006, "count": 932, "self": 8.494953712001006 } } }, "workers": { "total": 0.013869643998077663, "count": 932, "self": 0.0, "children": { "worker_root": { "total": 24.868073781995463, "count": 932, "is_parallel": true, "self": 14.013799128991195, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003067575999921246, "count": 1, "is_parallel": true, "self": 0.0007622169989645045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023053590009567415, "count": 10, "is_parallel": true, "self": 0.0023053590009567415 } } }, "UnityEnvironment.step": { "total": 0.03800216099989484, "count": 1, "is_parallel": true, "self": 0.0006384190000972012, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000414202000001751, "count": 1, "is_parallel": true, "self": 0.000414202000001751 }, "communicator.exchange": { "total": 0.0349666919998981, "count": 1, "is_parallel": true, "self": 0.0349666919998981 }, "steps_from_proto": { "total": 0.0019828479998977855, "count": 1, "is_parallel": true, "self": 0.00036528099985844165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016175670000393438, "count": 10, "is_parallel": true, "self": 0.0016175670000393438 } } } } } } }, "UnityEnvironment.step": { "total": 10.854274653004268, "count": 931, "is_parallel": true, "self": 0.527694120994056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2806934130016998, "count": 931, "is_parallel": true, "self": 0.2806934130016998 }, "communicator.exchange": { "total": 8.333602966999251, "count": 931, "is_parallel": true, "self": 8.333602966999251 }, "steps_from_proto": { "total": 1.7122841520092607, "count": 931, "is_parallel": true, "self": 0.31524731699096264, "children": { "_process_rank_one_or_two_observation": { "total": 1.397036835018298, "count": 9310, "is_parallel": true, "self": 1.397036835018298 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002192980000472744, "count": 1, "self": 0.0002192980000472744, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 21.809158544080447, "count": 37815, "is_parallel": true, "self": 0.7616994200357112, "children": { "process_trajectory": { "total": 12.65068600504469, "count": 37815, "is_parallel": true, "self": 12.65068600504469 }, "_update_policy": { "total": 8.396773119000045, "count": 4, "is_parallel": true, "self": 2.100224684003024, "children": { "TorchPPOOptimizer.update": { "total": 6.296548434997021, "count": 201, "is_parallel": true, "self": 6.296548434997021 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12359403599975849, "count": 1, "self": 0.0010294209996573045, "children": { "RLTrainer._checkpoint": { "total": 0.12256461500010118, "count": 1, "self": 0.12256461500010118 } } } } } } }