{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0739489793777466, "min": 1.0739489793777466, "max": 2.870185375213623, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10348.572265625, "min": 10348.572265625, "max": 29456.712890625, "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": 11.532469749450684, "min": 0.2966359555721283, "max": 11.532469749450684, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2248.83154296875, "min": 57.5473747253418, "max": 2333.341064453125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0635090301053852, "min": 0.06283494444123433, "max": 0.07571683054511417, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2540361204215408, "min": 0.2540361204215408, "max": 0.3785841527255709, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18106136591557193, "min": 0.14271169942666723, "max": 0.2715935118350328, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7242454636622877, "min": 0.5708467977066689, "max": 1.3579675591751639, "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.CumulativeReward.mean": { "value": 22.59090909090909, "min": 3.5, "max": 22.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 994.0, "min": 154.0, "max": 1250.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.59090909090909, "min": 3.5, "max": 22.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 994.0, "min": 154.0, "max": 1250.0, "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": "1709201642", "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=SnowballTarget1 --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": "1709202265" }, "total": 623.292134227, "count": 1, "self": 0.9606121510000776, "children": { "run_training.setup": { "total": 0.07698363800000152, "count": 1, "self": 0.07698363800000152 }, "TrainerController.start_learning": { "total": 622.2545384379999, "count": 1, "self": 0.9163002860075267, "children": { "TrainerController._reset_env": { "total": 4.642236251999975, "count": 1, "self": 4.642236251999975 }, "TrainerController.advance": { "total": 616.5320555609923, "count": 18217, "self": 0.4570199289883021, "children": { "env_step": { "total": 616.075035632004, "count": 18217, "self": 474.59927423001875, "children": { "SubprocessEnvManager._take_step": { "total": 141.02781691999326, "count": 18217, "self": 2.639395606991343, "children": { "TorchPolicy.evaluate": { "total": 138.3884213130019, "count": 18217, "self": 138.3884213130019 } } }, "workers": { "total": 0.4479444819919536, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 620.1672198569986, "count": 18217, "is_parallel": true, "self": 289.5845915409941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011090630000012425, "count": 1, "is_parallel": true, "self": 0.004871066000191604, "children": { "_process_rank_one_or_two_observation": { "total": 0.006219563999820821, "count": 10, "is_parallel": true, "self": 0.006219563999820821 } } }, "UnityEnvironment.step": { "total": 0.08916947000000164, "count": 1, "is_parallel": true, "self": 0.000884051999832991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005049380000627934, "count": 1, "is_parallel": true, "self": 0.0005049380000627934 }, "communicator.exchange": { "total": 0.08534005600006367, "count": 1, "is_parallel": true, "self": 0.08534005600006367 }, "steps_from_proto": { "total": 0.002440424000042185, "count": 1, "is_parallel": true, "self": 0.0004600590002610261, "children": { "_process_rank_one_or_two_observation": { "total": 0.001980364999781159, "count": 10, "is_parallel": true, "self": 0.001980364999781159 } } } } } } }, "UnityEnvironment.step": { "total": 330.5826283160045, "count": 18216, "is_parallel": true, "self": 16.322101720999626, "children": { "UnityEnvironment._generate_step_input": { "total": 8.217560641997238, "count": 18216, "is_parallel": true, "self": 8.217560641997238 }, "communicator.exchange": { "total": 259.11885284800917, "count": 18216, "is_parallel": true, "self": 259.11885284800917 }, "steps_from_proto": { "total": 46.92411310499847, "count": 18216, "is_parallel": true, "self": 9.479792601979057, "children": { "_process_rank_one_or_two_observation": { "total": 37.44432050301941, "count": 182160, "is_parallel": true, "self": 37.44432050301941 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019944600012422598, "count": 1, "self": 0.00019944600012422598, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 608.9130417580269, "count": 865742, "is_parallel": true, "self": 19.658567221042517, "children": { "process_trajectory": { "total": 326.9017357989843, "count": 865742, "is_parallel": true, "self": 326.0358627869841, "children": { "RLTrainer._checkpoint": { "total": 0.8658730120001792, "count": 4, "is_parallel": true, "self": 0.8658730120001792 } } }, "_update_policy": { "total": 262.3527387380001, "count": 90, "is_parallel": true, "self": 69.07964396198588, "children": { "TorchPPOOptimizer.update": { "total": 193.2730947760142, "count": 4584, "is_parallel": true, "self": 193.2730947760142 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1637468930000523, "count": 1, "self": 0.0017397810001966718, "children": { "RLTrainer._checkpoint": { "total": 0.16200711199985562, "count": 1, "self": 0.16200711199985562 } } } } } } }