{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0024819374084473, "min": 1.0024819374084473, "max": 2.8343214988708496, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9571.697265625, "min": 9571.697265625, "max": 29057.46484375, "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": 12.558521270751953, "min": 0.5962350368499756, "max": 12.558521270751953, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2448.91162109375, "min": 115.66959381103516, "max": 2548.076171875, "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": 0.0692246930629706, "min": 0.06191503521393529, "max": 0.07599236275521382, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2768987722518824, "min": 0.24766014085574117, "max": 0.3617230857452537, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20683902034572527, "min": 0.15129796514634553, "max": 0.3021167833723274, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8273560813829011, "min": 0.6051918605853821, "max": 1.3765856316860985, "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": 24.977272727272727, "min": 4.0227272727272725, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 177.0, "max": 1357.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 4.0227272727272725, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 177.0, "max": 1357.0, "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": "1709818043", "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": "1709818485" }, "total": 442.2531177500001, "count": 1, "self": 0.4323501680000845, "children": { "run_training.setup": { "total": 0.057899194000015086, "count": 1, "self": 0.057899194000015086 }, "TrainerController.start_learning": { "total": 441.762868388, "count": 1, "self": 0.569520807983622, "children": { "TrainerController._reset_env": { "total": 3.6453535070000953, "count": 1, "self": 3.6453535070000953 }, "TrainerController.advance": { "total": 437.45622971401644, "count": 18199, "self": 0.26164673603125266, "children": { "env_step": { "total": 437.1945829779852, "count": 18199, "self": 280.8524065210072, "children": { "SubprocessEnvManager._take_step": { "total": 156.06640351499846, "count": 18199, "self": 1.4369342390232305, "children": { "TorchPolicy.evaluate": { "total": 154.62946927597523, "count": 18199, "self": 154.62946927597523 } } }, "workers": { "total": 0.2757729419795396, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 440.64407975699214, "count": 18199, "is_parallel": true, "self": 221.1712799799909, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006636137999976199, "count": 1, "is_parallel": true, "self": 0.005029937000017526, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016062009999586735, "count": 10, "is_parallel": true, "self": 0.0016062009999586735 } } }, "UnityEnvironment.step": { "total": 0.03786901499995565, "count": 1, "is_parallel": true, "self": 0.000671159999910742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004043960000217339, "count": 1, "is_parallel": true, "self": 0.0004043960000217339 }, "communicator.exchange": { "total": 0.03469156699998166, "count": 1, "is_parallel": true, "self": 0.03469156699998166 }, "steps_from_proto": { "total": 0.0021018920000415164, "count": 1, "is_parallel": true, "self": 0.00039617500033273245, "children": { "_process_rank_one_or_two_observation": { "total": 0.001705716999708784, "count": 10, "is_parallel": true, "self": 0.001705716999708784 } } } } } } }, "UnityEnvironment.step": { "total": 219.47279977700123, "count": 18198, "is_parallel": true, "self": 10.152328071999591, "children": { "UnityEnvironment._generate_step_input": { "total": 5.314615579997621, "count": 18198, "is_parallel": true, "self": 5.314615579997621 }, "communicator.exchange": { "total": 170.8303680750123, "count": 18198, "is_parallel": true, "self": 170.8303680750123 }, "steps_from_proto": { "total": 33.17548804999171, "count": 18198, "is_parallel": true, "self": 6.129626140935784, "children": { "_process_rank_one_or_two_observation": { "total": 27.04586190905593, "count": 181980, "is_parallel": true, "self": 27.04586190905593 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013861599995834695, "count": 1, "self": 0.00013861599995834695, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.8274472639963, "count": 669926, "is_parallel": true, "self": 14.801026578048777, "children": { "process_trajectory": { "total": 237.98511871694802, "count": 669926, "is_parallel": true, "self": 237.21292804394773, "children": { "RLTrainer._checkpoint": { "total": 0.7721906730002956, "count": 4, "is_parallel": true, "self": 0.7721906730002956 } } }, "_update_policy": { "total": 179.0413019689995, "count": 90, "is_parallel": true, "self": 51.055400786000405, "children": { "TorchPPOOptimizer.update": { "total": 127.9859011829991, "count": 4587, "is_parallel": true, "self": 127.9859011829991 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09162574299989501, "count": 1, "self": 0.001032843999837496, "children": { "RLTrainer._checkpoint": { "total": 0.09059289900005751, "count": 1, "self": 0.09059289900005751 } } } } } } }