{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9963166117668152, "min": 0.9905362725257874, "max": 2.8670003414154053, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9534.75, "min": 9534.75, "max": 29392.48828125, "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": 11.952459335327148, "min": 0.25911644101142883, "max": 11.952459335327148, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2330.7294921875, "min": 50.26858901977539, "max": 2398.29345703125, "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": 0.06682561780411667, "min": 0.061078644540376606, "max": 0.07419023801915448, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26730247121646666, "min": 0.24431457816150642, "max": 0.3655648074094572, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1965885212754502, "min": 0.12260980946331412, "max": 0.27555190815645103, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7863540851018008, "min": 0.4904392378532565, "max": 1.3777595407822552, "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": 23.454545454545453, "min": 3.5454545454545454, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1032.0, "min": 156.0, "max": 1283.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.454545454545453, "min": 3.5454545454545454, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1032.0, "min": 156.0, "max": 1283.0, "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": "1687887997", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1687888459" }, "total": 461.43691664499994, "count": 1, "self": 0.7457309019999343, "children": { "run_training.setup": { "total": 0.04058223800001315, "count": 1, "self": 0.04058223800001315 }, "TrainerController.start_learning": { "total": 460.650603505, "count": 1, "self": 0.5631340929985527, "children": { "TrainerController._reset_env": { "total": 4.07799388799998, "count": 1, "self": 4.07799388799998 }, "TrainerController.advance": { "total": 455.7914760240013, "count": 18223, "self": 0.2582649989998913, "children": { "env_step": { "total": 455.53321102500144, "count": 18223, "self": 330.88269851300544, "children": { "SubprocessEnvManager._take_step": { "total": 124.3858367069995, "count": 18223, "self": 1.855366405991731, "children": { "TorchPolicy.evaluate": { "total": 122.53047030100777, "count": 18223, "self": 122.53047030100777 } } }, "workers": { "total": 0.2646758049965001, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 459.07896402200646, "count": 18223, "is_parallel": true, "self": 214.00918233100953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005521530999999413, "count": 1, "is_parallel": true, "self": 0.0040852989999393685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014362320000600448, "count": 10, "is_parallel": true, "self": 0.0014362320000600448 } } }, "UnityEnvironment.step": { "total": 0.03323361200000363, "count": 1, "is_parallel": true, "self": 0.0006009919999883095, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003037000000176704, "count": 1, "is_parallel": true, "self": 0.0003037000000176704 }, "communicator.exchange": { "total": 0.03030741399999215, "count": 1, "is_parallel": true, "self": 0.03030741399999215 }, "steps_from_proto": { "total": 0.002021506000005502, "count": 1, "is_parallel": true, "self": 0.0003677920001337043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016537139998717976, "count": 10, "is_parallel": true, "self": 0.0016537139998717976 } } } } } } }, "UnityEnvironment.step": { "total": 245.06978169099693, "count": 18222, "is_parallel": true, "self": 10.126104353008827, "children": { "UnityEnvironment._generate_step_input": { "total": 5.101841001994956, "count": 18222, "is_parallel": true, "self": 5.101841001994956 }, "communicator.exchange": { "total": 196.3372398639949, "count": 18222, "is_parallel": true, "self": 196.3372398639949 }, "steps_from_proto": { "total": 33.50459647199824, "count": 18222, "is_parallel": true, "self": 6.057669319007005, "children": { "_process_rank_one_or_two_observation": { "total": 27.446927152991236, "count": 182220, "is_parallel": true, "self": 27.446927152991236 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.26610000533401e-05, "count": 1, "self": 9.26610000533401e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.3818990419458, "count": 447928, "is_parallel": true, "self": 9.54594585398712, "children": { "process_trajectory": { "total": 249.1965570909594, "count": 447928, "is_parallel": true, "self": 247.97315170995944, "children": { "RLTrainer._checkpoint": { "total": 1.2234053809999637, "count": 4, "is_parallel": true, "self": 1.2234053809999637 } } }, "_update_policy": { "total": 193.6393960969993, "count": 90, "is_parallel": true, "self": 73.39280499899684, "children": { "TorchPPOOptimizer.update": { "total": 120.24659109800245, "count": 4587, "is_parallel": true, "self": 120.24659109800245 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21790683900007934, "count": 1, "self": 0.0011051669999915248, "children": { "RLTrainer._checkpoint": { "total": 0.21680167200008782, "count": 1, "self": 0.21680167200008782 } } } } } } }