{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9114164710044861, "min": 0.9114164710044861, "max": 2.850888729095459, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8742.306640625, "min": 8742.306640625, "max": 29133.232421875, "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": 12.32719612121582, "min": 0.5544964075088501, "max": 12.343586921691895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2403.80322265625, "min": 107.57230377197266, "max": 2518.091796875, "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": 0.07097194655872562, "min": 0.061566012560540596, "max": 0.07444621999899277, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28388778623490246, "min": 0.2514840609196564, "max": 0.3540046336494532, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2120452010091029, "min": 0.12451360267404393, "max": 0.28790811809035494, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8481808040364116, "min": 0.49805441069617573, "max": 1.4395405904517746, "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": 24.386363636363637, "min": 3.590909090909091, "max": 24.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1073.0, "min": 158.0, "max": 1329.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.386363636363637, "min": 3.590909090909091, "max": 24.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1073.0, "min": 158.0, "max": 1329.0, "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": "1715088670", "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": "1715089111" }, "total": 441.05968849, "count": 1, "self": 0.6382215380000389, "children": { "run_training.setup": { "total": 0.05616749600000048, "count": 1, "self": 0.05616749600000048 }, "TrainerController.start_learning": { "total": 440.36529945599995, "count": 1, "self": 0.5671936910043769, "children": { "TrainerController._reset_env": { "total": 3.115964252000026, "count": 1, "self": 3.115964252000026 }, "TrainerController.advance": { "total": 436.55015071799556, "count": 18210, "self": 0.27735859498841364, "children": { "env_step": { "total": 436.27279212300715, "count": 18210, "self": 283.4800585959978, "children": { "SubprocessEnvManager._take_step": { "total": 152.50878437100545, "count": 18210, "self": 1.4349542760076588, "children": { "TorchPolicy.evaluate": { "total": 151.0738300949978, "count": 18210, "self": 151.0738300949978 } } }, "workers": { "total": 0.2839491560039278, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 439.01607410299454, "count": 18210, "is_parallel": true, "self": 218.3439937029936, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007489327999962825, "count": 1, "is_parallel": true, "self": 0.005945123999936186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015442040000266388, "count": 10, "is_parallel": true, "self": 0.0015442040000266388 } } }, "UnityEnvironment.step": { "total": 0.03621901400003935, "count": 1, "is_parallel": true, "self": 0.0007393880000563513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040211900000031164, "count": 1, "is_parallel": true, "self": 0.00040211900000031164 }, "communicator.exchange": { "total": 0.03289479299996856, "count": 1, "is_parallel": true, "self": 0.03289479299996856 }, "steps_from_proto": { "total": 0.00218271400001413, "count": 1, "is_parallel": true, "self": 0.0005401410000445139, "children": { "_process_rank_one_or_two_observation": { "total": 0.001642572999969616, "count": 10, "is_parallel": true, "self": 0.001642572999969616 } } } } } } }, "UnityEnvironment.step": { "total": 220.67208040000094, "count": 18209, "is_parallel": true, "self": 10.15238089100552, "children": { "UnityEnvironment._generate_step_input": { "total": 5.255988469002034, "count": 18209, "is_parallel": true, "self": 5.255988469002034 }, "communicator.exchange": { "total": 172.20934739800185, "count": 18209, "is_parallel": true, "self": 172.20934739800185 }, "steps_from_proto": { "total": 33.05436364199153, "count": 18209, "is_parallel": true, "self": 6.15494090500647, "children": { "_process_rank_one_or_two_observation": { "total": 26.89942273698506, "count": 182090, "is_parallel": true, "self": 26.89942273698506 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014725400001225353, "count": 1, "self": 0.00014725400001225353, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.27364601300957, "count": 669531, "is_parallel": true, "self": 13.55118924900927, "children": { "process_trajectory": { "total": 238.83942737000018, "count": 669531, "is_parallel": true, "self": 237.74473001700005, "children": { "RLTrainer._checkpoint": { "total": 1.0946973530001287, "count": 4, "is_parallel": true, "self": 1.0946973530001287 } } }, "_update_policy": { "total": 178.88302939400012, "count": 90, "is_parallel": true, "self": 52.465243658993984, "children": { "TorchPPOOptimizer.update": { "total": 126.41778573500613, "count": 4584, "is_parallel": true, "self": 126.41778573500613 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13184354099996654, "count": 1, "self": 0.001292110999884244, "children": { "RLTrainer._checkpoint": { "total": 0.1305514300000823, "count": 1, "self": 0.1305514300000823 } } } } } } }