{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.907183825969696, "min": 0.907183825969696, "max": 2.874448299407959, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8681.7490234375, "min": 8681.7490234375, "max": 29468.84375, "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": 12.969823837280273, "min": 0.31671142578125, "max": 12.969823837280273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.11572265625, "min": 61.4420166015625, "max": 2613.793212890625, "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.Losses.PolicyLoss.mean": { "value": 0.07369898600197357, "min": 0.06299902862297398, "max": 0.07558964983875152, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2947959440078943, "min": 0.25790870081868444, "max": 0.3779482491937576, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1996977282140185, "min": 0.10328789996485427, "max": 0.26713508986959267, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.798790912856074, "min": 0.4131515998594171, "max": 1.3356754493479635, "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": 25.295454545454547, "min": 2.8863636363636362, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 127.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 2.8863636363636362, "max": 25.327272727272728, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 127.0, "max": 1393.0, "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": "1713783786", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/neptun/PycharmProjects/rlcourse/.venv/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": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713784275" }, "total": 488.8364282500006, "count": 1, "self": 0.37236085399854346, "children": { "run_training.setup": { "total": 0.033199987999978475, "count": 1, "self": 0.033199987999978475 }, "TrainerController.start_learning": { "total": 488.4308674080021, "count": 1, "self": 0.5221897921619529, "children": { "TrainerController._reset_env": { "total": 1.5690138960017066, "count": 1, "self": 1.5690138960017066 }, "TrainerController.advance": { "total": 486.2389567128339, "count": 18201, "self": 0.2556653957362869, "children": { "env_step": { "total": 485.9832913170976, "count": 18201, "self": 353.6779834014269, "children": { "SubprocessEnvManager._take_step": { "total": 132.02554884968777, "count": 18201, "self": 1.399545068576117, "children": { "TorchPolicy.evaluate": { "total": 130.62600378111165, "count": 18201, "self": 130.62600378111165 } } }, "workers": { "total": 0.27975906598294387, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 487.6171488656946, "count": 18201, "is_parallel": true, "self": 217.460251788787, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002460936000716174, "count": 1, "is_parallel": true, "self": 0.0011119230002805125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013490130004356615, "count": 10, "is_parallel": true, "self": 0.0013490130004356615 } } }, "UnityEnvironment.step": { "total": 0.028695718003291404, "count": 1, "is_parallel": true, "self": 0.00039526000546175055, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005382630006351974, "count": 1, "is_parallel": true, "self": 0.0005382630006351974 }, "communicator.exchange": { "total": 0.02662075599801028, "count": 1, "is_parallel": true, "self": 0.02662075599801028 }, "steps_from_proto": { "total": 0.0011414389991841745, "count": 1, "is_parallel": true, "self": 0.000247009997110581, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008944290020735934, "count": 10, "is_parallel": true, "self": 0.0008944290020735934 } } } } } } }, "UnityEnvironment.step": { "total": 270.1568970769076, "count": 18200, "is_parallel": true, "self": 12.592011873133742, "children": { "UnityEnvironment._generate_step_input": { "total": 7.363880842549406, "count": 18200, "is_parallel": true, "self": 7.363880842549406 }, "communicator.exchange": { "total": 213.5594151550249, "count": 18200, "is_parallel": true, "self": 213.5594151550249 }, "steps_from_proto": { "total": 36.64158920619957, "count": 18200, "is_parallel": true, "self": 7.238067337220855, "children": { "_process_rank_one_or_two_observation": { "total": 29.403521868978714, "count": 182000, "is_parallel": true, "self": 29.403521868978714 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001237050018971786, "count": 1, "self": 0.0001237050018971786, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.4061661476371, "count": 488769, "is_parallel": true, "self": 12.047958059563825, "children": { "process_trajectory": { "total": 267.6887475640542, "count": 488769, "is_parallel": true, "self": 267.1457677640501, "children": { "RLTrainer._checkpoint": { "total": 0.5429798000041046, "count": 4, "is_parallel": true, "self": 0.5429798000041046 } } }, "_update_policy": { "total": 201.6694605240191, "count": 90, "is_parallel": true, "self": 41.062720140078454, "children": { "TorchPPOOptimizer.update": { "total": 160.60674038394063, "count": 4587, "is_parallel": true, "self": 160.60674038394063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10058330200263299, "count": 1, "self": 0.0011956630005443003, "children": { "RLTrainer._checkpoint": { "total": 0.09938763900208869, "count": 1, "self": 0.09938763900208869 } } } } } } }