{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8536158800125122, "min": 0.8384495377540588, "max": 2.8674020767211914, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8150.32421875, "min": 8150.32421875, "max": 29396.60546875, "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": 13.143617630004883, "min": 0.27994483709335327, "max": 13.143617630004883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2563.00537109375, "min": 54.309295654296875, "max": 2641.72509765625, "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": 0.06506835122269752, "min": 0.06222033383628335, "max": 0.07205073453637761, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2602734048907901, "min": 0.2488813353451334, "max": 0.35537944188356907, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1897501792831748, "min": 0.09343045601374744, "max": 0.28749331152614427, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7590007171326992, "min": 0.37372182405498977, "max": 1.405483903838139, "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": 25.886363636363637, "min": 2.6136363636363638, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 115.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 2.6136363636363638, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 115.0, "max": 1422.0, "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": "1673477666", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673478083" }, "total": 416.7373653579999, "count": 1, "self": 0.38597027399976014, "children": { "run_training.setup": { "total": 0.10814696300008109, "count": 1, "self": 0.10814696300008109 }, "TrainerController.start_learning": { "total": 416.2432481210001, "count": 1, "self": 0.5044450060116787, "children": { "TrainerController._reset_env": { "total": 6.878073202999985, "count": 1, "self": 6.878073202999985 }, "TrainerController.advance": { "total": 408.7451265829885, "count": 18200, "self": 0.25029773900507735, "children": { "env_step": { "total": 408.49482884398344, "count": 18200, "self": 266.22424342701504, "children": { "SubprocessEnvManager._take_step": { "total": 142.01334912500204, "count": 18200, "self": 1.3521023780065207, "children": { "TorchPolicy.evaluate": { "total": 140.66124674699552, "count": 18200, "self": 30.97845003997827, "children": { "TorchPolicy.sample_actions": { "total": 109.68279670701725, "count": 18200, "self": 109.68279670701725 } } } } }, "workers": { "total": 0.25723629196636466, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 415.06109935399877, "count": 18200, "is_parallel": true, "self": 201.93562726598998, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005984882000007019, "count": 1, "is_parallel": true, "self": 0.0035615389999748004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024233430000322187, "count": 10, "is_parallel": true, "self": 0.0024233430000322187 } } }, "UnityEnvironment.step": { "total": 0.048694766000039635, "count": 1, "is_parallel": true, "self": 0.00041715700012900925, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026463299991519307, "count": 1, "is_parallel": true, "self": 0.00026463299991519307 }, "communicator.exchange": { "total": 0.04643785899997965, "count": 1, "is_parallel": true, "self": 0.04643785899997965 }, "steps_from_proto": { "total": 0.00157511700001578, "count": 1, "is_parallel": true, "self": 0.0003957899998567882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011793270001589917, "count": 10, "is_parallel": true, "self": 0.0011793270001589917 } } } } } } }, "UnityEnvironment.step": { "total": 213.1254720880088, "count": 18199, "is_parallel": true, "self": 8.153688310981579, "children": { "UnityEnvironment._generate_step_input": { "total": 4.7843069880044595, "count": 18199, "is_parallel": true, "self": 4.7843069880044595 }, "communicator.exchange": { "total": 171.05473109200648, "count": 18199, "is_parallel": true, "self": 171.05473109200648 }, "steps_from_proto": { "total": 29.132745697016276, "count": 18199, "is_parallel": true, "self": 6.151028559003521, "children": { "_process_rank_one_or_two_observation": { "total": 22.981717138012755, "count": 181990, "is_parallel": true, "self": 22.981717138012755 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.3260999973426806e-05, "count": 1, "self": 4.3260999973426806e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 405.91689609694333, "count": 330231, "is_parallel": true, "self": 8.335103197997455, "children": { "process_trajectory": { "total": 231.5312971239474, "count": 330231, "is_parallel": true, "self": 230.51219123994758, "children": { "RLTrainer._checkpoint": { "total": 1.0191058839998277, "count": 4, "is_parallel": true, "self": 1.0191058839998277 } } }, "_update_policy": { "total": 166.05049577499847, "count": 90, "is_parallel": true, "self": 47.0128386839956, "children": { "TorchPPOOptimizer.update": { "total": 119.03765709100287, "count": 4587, "is_parallel": true, "self": 119.03765709100287 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11556006799992247, "count": 1, "self": 0.0008240709998972306, "children": { "RLTrainer._checkpoint": { "total": 0.11473599700002524, "count": 1, "self": 0.11473599700002524 } } } } } } }