{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.192570447921753, "min": 1.192570447921753, "max": 2.8709208965301514, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11386.6630859375, "min": 11386.6630859375, "max": 29464.26171875, "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": 12.416328430175781, "min": 0.34186267852783203, "max": 12.416328430175781, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2421.18408203125, "min": 66.32135772705078, "max": 2474.7236328125, "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": 0.07160788819943692, "min": 0.06182434910996224, "max": 0.07552313604019575, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2864315527977477, "min": 0.2603589579526919, "max": 0.37075133292648177, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20920054797156185, "min": 0.10199452318164393, "max": 0.2710055428977106, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8368021918862474, "min": 0.4079780927265757, "max": 1.3550277144885532, "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": 24.818181818181817, "min": 3.022727272727273, "max": 24.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 133.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.022727272727273, "max": 24.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 133.0, "max": 1369.0, "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": "1691738530", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691739144" }, "total": 614.0951209070001, "count": 1, "self": 0.48467493500015735, "children": { "run_training.setup": { "total": 0.0513437749999639, "count": 1, "self": 0.0513437749999639 }, "TrainerController.start_learning": { "total": 613.559102197, "count": 1, "self": 0.7442223630101807, "children": { "TrainerController._reset_env": { "total": 4.531621370000039, "count": 1, "self": 4.531621370000039 }, "TrainerController.advance": { "total": 608.1113396889898, "count": 18201, "self": 0.38827468898227835, "children": { "env_step": { "total": 607.7230650000075, "count": 18201, "self": 445.4055245530092, "children": { "SubprocessEnvManager._take_step": { "total": 161.93070016299305, "count": 18201, "self": 2.4044273309868913, "children": { "TorchPolicy.evaluate": { "total": 159.52627283200616, "count": 18201, "self": 159.52627283200616 } } }, "workers": { "total": 0.38684028400530224, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 611.2985656269996, "count": 18201, "is_parallel": true, "self": 280.93926640799134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006881153999984235, "count": 1, "is_parallel": true, "self": 0.004502853999724721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023783000002595145, "count": 10, "is_parallel": true, "self": 0.0023783000002595145 } } }, "UnityEnvironment.step": { "total": 0.043135624999990796, "count": 1, "is_parallel": true, "self": 0.0007209410000541538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040136299992354907, "count": 1, "is_parallel": true, "self": 0.00040136299992354907 }, "communicator.exchange": { "total": 0.03925690200003373, "count": 1, "is_parallel": true, "self": 0.03925690200003373 }, "steps_from_proto": { "total": 0.00275641899997936, "count": 1, "is_parallel": true, "self": 0.000487496999880932, "children": { "_process_rank_one_or_two_observation": { "total": 0.002268922000098428, "count": 10, "is_parallel": true, "self": 0.002268922000098428 } } } } } } }, "UnityEnvironment.step": { "total": 330.3592992190082, "count": 18200, "is_parallel": true, "self": 13.638666807984805, "children": { "UnityEnvironment._generate_step_input": { "total": 6.967314531009492, "count": 18200, "is_parallel": true, "self": 6.967314531009492 }, "communicator.exchange": { "total": 258.9714585319982, "count": 18200, "is_parallel": true, "self": 258.9714585319982 }, "steps_from_proto": { "total": 50.7818593480157, "count": 18200, "is_parallel": true, "self": 9.750223618998575, "children": { "_process_rank_one_or_two_observation": { "total": 41.031635729017125, "count": 182000, "is_parallel": true, "self": 41.031635729017125 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013024600002609077, "count": 1, "self": 0.00013024600002609077, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 602.5767582299885, "count": 586137, "is_parallel": true, "self": 15.288131466964728, "children": { "process_trajectory": { "total": 332.3007224580224, "count": 586137, "is_parallel": true, "self": 330.8306985780225, "children": { "RLTrainer._checkpoint": { "total": 1.4700238799998715, "count": 4, "is_parallel": true, "self": 1.4700238799998715 } } }, "_update_policy": { "total": 254.9879043050014, "count": 90, "is_parallel": true, "self": 104.95914042400511, "children": { "TorchPPOOptimizer.update": { "total": 150.02876388099628, "count": 4587, "is_parallel": true, "self": 150.02876388099628 } } } } } } } } }, "TrainerController._save_models": { "total": 0.17178852899996855, "count": 1, "self": 0.001000697999870681, "children": { "RLTrainer._checkpoint": { "total": 0.17078783100009787, "count": 1, "self": 0.17078783100009787 } } } } } } }