{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5554143786430359, "min": 0.5431214570999146, "max": 0.8691041469573975, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5351.97314453125, "min": 5228.943359375, "max": 8976.9765625, "count": 30 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.531689643859863, "min": 12.990665435791016, "max": 13.649582862854004, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2760.464599609375, "min": 2494.838134765625, "max": 2784.514892578125, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0689360275408855, "min": 0.06196786984219216, "max": 0.08477714681004156, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3446801377044275, "min": 0.24787147936876863, "max": 0.3776190985734894, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17166311223717298, "min": 0.1591150899801184, "max": 0.21358135138072218, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8583155611858649, "min": 0.6364603599204736, "max": 0.9760537848753088, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.1056989647999945e-06, "min": 3.1056989647999945e-06, "max": 0.00017668564110480002, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5528494823999972e-05, "min": 1.5528494823999972e-05, "max": 0.000853728215424, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103520000000002, "min": 0.10103520000000002, "max": 0.15889520000000001, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5051760000000001, "min": 0.4120608, "max": 0.7845760000000002, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.165647999999992e-05, "min": 6.165647999999992e-05, "max": 0.002948870480000001, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003082823999999996, "min": 0.0003082823999999996, "max": 0.0142503424, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.254545454545454, "min": 25.072727272727274, "max": 26.818181818181817, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1444.0, "min": 1137.0, "max": 1472.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.254545454545454, "min": 25.072727272727274, "max": 26.818181818181817, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1444.0, "min": 1137.0, "max": 1472.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688361359", "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 --resume", "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": "1688362084" }, "total": 725.1287801450001, "count": 1, "self": 0.42301487899976564, "children": { "run_training.setup": { "total": 0.03936998600011066, "count": 1, "self": 0.03936998600011066 }, "TrainerController.start_learning": { "total": 724.6663952800002, "count": 1, "self": 0.8414607440045074, "children": { "TrainerController._reset_env": { "total": 3.9242372219998742, "count": 1, "self": 3.9242372219998742 }, "TrainerController.advance": { "total": 719.7430740599957, "count": 27274, "self": 0.42077153500281383, "children": { "env_step": { "total": 719.3223025249929, "count": 27274, "self": 524.3226615199812, "children": { "SubprocessEnvManager._take_step": { "total": 194.58223836600496, "count": 27274, "self": 2.794133769002201, "children": { "TorchPolicy.evaluate": { "total": 191.78810459700276, "count": 27274, "self": 191.78810459700276 } } }, "workers": { "total": 0.4174026390066956, "count": 27274, "self": 0.0, "children": { "worker_root": { "total": 722.2940654699773, "count": 27274, "is_parallel": true, "self": 337.9235702160188, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001969485000017812, "count": 1, "is_parallel": true, "self": 0.0005988259999867296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013706590000310825, "count": 10, "is_parallel": true, "self": 0.0013706590000310825 } } }, "UnityEnvironment.step": { "total": 0.08242344599989337, "count": 1, "is_parallel": true, "self": 0.0006884039999022207, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045308199992177833, "count": 1, "is_parallel": true, "self": 0.00045308199992177833 }, "communicator.exchange": { "total": 0.07630878300005861, "count": 1, "is_parallel": true, "self": 0.07630878300005861 }, "steps_from_proto": { "total": 0.0049731770000107645, "count": 1, "is_parallel": true, "self": 0.002791672000057588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021815049999531766, "count": 10, "is_parallel": true, "self": 0.0021815049999531766 } } } } } } }, "UnityEnvironment.step": { "total": 384.37049525395855, "count": 27273, "is_parallel": true, "self": 15.486524079959281, "children": { "UnityEnvironment._generate_step_input": { "total": 8.425367698016771, "count": 27273, "is_parallel": true, "self": 8.425367698016771 }, "communicator.exchange": { "total": 305.2477889279937, "count": 27273, "is_parallel": true, "self": 305.2477889279937 }, "steps_from_proto": { "total": 55.210814547988775, "count": 27273, "is_parallel": true, "self": 10.211360998963528, "children": { "_process_rank_one_or_two_observation": { "total": 44.99945354902525, "count": 272730, "is_parallel": true, "self": 44.99945354902525 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.70650000149908e-05, "count": 1, "self": 3.70650000149908e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 714.1417267301904, "count": 684441, "is_parallel": true, "self": 15.42709771122577, "children": { "process_trajectory": { "total": 390.330625886965, "count": 684441, "is_parallel": true, "self": 388.8141920999649, "children": { "RLTrainer._checkpoint": { "total": 1.5164337870000963, "count": 6, "is_parallel": true, "self": 1.5164337870000963 } } }, "_update_policy": { "total": 308.38400313199963, "count": 136, "is_parallel": true, "self": 119.26334611800644, "children": { "TorchPPOOptimizer.update": { "total": 189.1206570139932, "count": 6933, "is_parallel": true, "self": 189.1206570139932 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15758618900008514, "count": 1, "self": 0.0010900650001985923, "children": { "RLTrainer._checkpoint": { "total": 0.15649612399988655, "count": 1, "self": 0.15649612399988655 } } } } } } }