{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7039458155632019, "min": 0.6910336017608643, "max": 2.868377685546875, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6806.4521484375, "min": 6571.7109375, "max": 29501.263671875, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.534160614013672, "min": 0.23622384667396545, "max": 12.652727127075195, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2569.5029296875, "min": 45.82742691040039, "max": 2581.15625, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06591787617615802, "min": 0.06217343750005752, "max": 0.07521723206661465, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3295893808807901, "min": 0.24869375000023008, "max": 0.3760861603330733, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15028372713748145, "min": 0.07531981161902841, "max": 0.22346238777333616, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7514186356874073, "min": 0.30127924647611365, "max": 1.1073253562162613, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.8, "min": 2.75, "max": 28.054545454545455, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1474.0, "min": 121.0, "max": 1543.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.11999973600561, "min": 2.4749999154697764, "max": 25.249090645530007, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1326.5999854803085, "min": 108.89999628067017, "max": 1388.6999855041504, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698235062", "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=SnowballTarget10 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698236243" }, "total": 1181.4154204729998, "count": 1, "self": 0.42400241399946026, "children": { "run_training.setup": { "total": 0.07245913799988557, "count": 1, "self": 0.07245913799988557 }, "TrainerController.start_learning": { "total": 1180.9189589210005, "count": 1, "self": 1.3808948559753844, "children": { "TrainerController._reset_env": { "total": 4.027196734000427, "count": 1, "self": 4.027196734000427 }, "TrainerController.advance": { "total": 1175.361610602025, "count": 45475, "self": 0.6810732510512025, "children": { "env_step": { "total": 1174.6805373509737, "count": 45475, "self": 799.9916661069601, "children": { "SubprocessEnvManager._take_step": { "total": 373.96756045301936, "count": 45475, "self": 3.575356804013609, "children": { "TorchPolicy.evaluate": { "total": 370.39220364900575, "count": 45475, "self": 370.39220364900575 } } }, "workers": { "total": 0.7213107909942664, "count": 45475, "self": 0.0, "children": { "worker_root": { "total": 1177.6528284700034, "count": 45475, "is_parallel": true, "self": 575.1378572110198, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027449680001154775, "count": 1, "is_parallel": true, "self": 0.0007335599993893993, "children": { "_process_rank_one_or_two_observation": { "total": 0.002011408000726078, "count": 10, "is_parallel": true, "self": 0.002011408000726078 } } }, "UnityEnvironment.step": { "total": 0.03838495099989814, "count": 1, "is_parallel": true, "self": 0.0006239849994926772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028046399984305026, "count": 1, "is_parallel": true, "self": 0.00028046399984305026 }, "communicator.exchange": { "total": 0.03364752200013754, "count": 1, "is_parallel": true, "self": 0.03364752200013754 }, "steps_from_proto": { "total": 0.003832980000424868, "count": 1, "is_parallel": true, "self": 0.002323354000054678, "children": { "_process_rank_one_or_two_observation": { "total": 0.00150962600037019, "count": 10, "is_parallel": true, "self": 0.00150962600037019 } } } } } } }, "UnityEnvironment.step": { "total": 602.5149712589837, "count": 45474, "is_parallel": true, "self": 26.309160912030165, "children": { "UnityEnvironment._generate_step_input": { "total": 13.635493777052943, "count": 45474, "is_parallel": true, "self": 13.635493777052943 }, "communicator.exchange": { "total": 475.34554686696674, "count": 45474, "is_parallel": true, "self": 475.34554686696674 }, "steps_from_proto": { "total": 87.22476970293383, "count": 45474, "is_parallel": true, "self": 16.592675330822658, "children": { "_process_rank_one_or_two_observation": { "total": 70.63209437211117, "count": 454740, "is_parallel": true, "self": 70.63209437211117 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014823999936197652, "count": 1, "self": 0.00014823999936197652, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1165.5492370011157, "count": 1174333, "is_parallel": true, "self": 26.644801093040314, "children": { "process_trajectory": { "total": 654.8713894590719, "count": 1174333, "is_parallel": true, "self": 651.8696552830734, "children": { "RLTrainer._checkpoint": { "total": 3.0017341759985356, "count": 10, "is_parallel": true, "self": 3.0017341759985356 } } }, "_update_policy": { "total": 484.03304644900345, "count": 227, "is_parallel": true, "self": 140.0830618839609, "children": { "TorchPPOOptimizer.update": { "total": 343.94998456504254, "count": 11571, "is_parallel": true, "self": 343.94998456504254 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1491084890003549, "count": 1, "self": 0.0023446210007023183, "children": { "RLTrainer._checkpoint": { "total": 0.14676386799965258, "count": 1, "self": 0.14676386799965258 } } } } } } }