{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9203253984451294, "min": 0.9203253984451294, "max": 2.87199068069458, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8797.390625, "min": 8797.390625, "max": 29412.056640625, "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": 12.746652603149414, "min": 0.3289918005466461, "max": 12.746652603149414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2485.59716796875, "min": 63.82440948486328, "max": 2573.130859375, "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": 0.0709134438072272, "min": 0.06057916948342537, "max": 0.07506772596834173, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2836537752289088, "min": 0.24231667793370149, "max": 0.3753386298417086, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2378304643812133, "min": 0.11141798085551344, "max": 0.3040041479994269, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9513218575248532, "min": 0.44567192342205375, "max": 1.5200207399971344, "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": 24.954545454545453, "min": 3.2954545454545454, "max": 25.036363636363635, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 145.0, "max": 1377.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.2954545454545454, "max": 25.036363636363635, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 145.0, "max": 1377.0, "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": "1700138729", "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": "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": "1700139242" }, "total": 513.4855945059999, "count": 1, "self": 0.42427600799976517, "children": { "run_training.setup": { "total": 0.04409661300007883, "count": 1, "self": 0.04409661300007883 }, "TrainerController.start_learning": { "total": 513.017221885, "count": 1, "self": 0.595968730023742, "children": { "TrainerController._reset_env": { "total": 3.403739610999992, "count": 1, "self": 3.403739610999992 }, "TrainerController.advance": { "total": 508.9204661419765, "count": 18200, "self": 0.2899552909565273, "children": { "env_step": { "total": 508.63051085101995, "count": 18200, "self": 350.9300083590276, "children": { "SubprocessEnvManager._take_step": { "total": 157.39893257801157, "count": 18200, "self": 1.5612542330076167, "children": { "TorchPolicy.evaluate": { "total": 155.83767834500395, "count": 18200, "self": 155.83767834500395 } } }, "workers": { "total": 0.3015699139807566, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 511.5460948280115, "count": 18200, "is_parallel": true, "self": 247.2066387400164, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022803599999861035, "count": 1, "is_parallel": true, "self": 0.0008264189999636073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014539410000224962, "count": 10, "is_parallel": true, "self": 0.0014539410000224962 } } }, "UnityEnvironment.step": { "total": 0.037473795999972026, "count": 1, "is_parallel": true, "self": 0.0006077759999243426, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042677999999796157, "count": 1, "is_parallel": true, "self": 0.00042677999999796157 }, "communicator.exchange": { "total": 0.03437369300002047, "count": 1, "is_parallel": true, "self": 0.03437369300002047 }, "steps_from_proto": { "total": 0.0020655470000292553, "count": 1, "is_parallel": true, "self": 0.0004143949998933749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016511520001358804, "count": 10, "is_parallel": true, "self": 0.0016511520001358804 } } } } } } }, "UnityEnvironment.step": { "total": 264.33945608799513, "count": 18199, "is_parallel": true, "self": 11.44401565199803, "children": { "UnityEnvironment._generate_step_input": { "total": 5.931437674003291, "count": 18199, "is_parallel": true, "self": 5.931437674003291 }, "communicator.exchange": { "total": 208.68258799398927, "count": 18199, "is_parallel": true, "self": 208.68258799398927 }, "steps_from_proto": { "total": 38.28141476800454, "count": 18199, "is_parallel": true, "self": 7.233640183068701, "children": { "_process_rank_one_or_two_observation": { "total": 31.047774584935837, "count": 181990, "is_parallel": true, "self": 31.047774584935837 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.963799986195227e-05, "count": 1, "self": 3.963799986195227e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 504.2663183030718, "count": 529695, "is_parallel": true, "self": 12.406375989154753, "children": { "process_trajectory": { "total": 283.8029287069156, "count": 529695, "is_parallel": true, "self": 283.3052472749156, "children": { "RLTrainer._checkpoint": { "total": 0.4976814320000358, "count": 4, "is_parallel": true, "self": 0.4976814320000358 } } }, "_update_policy": { "total": 208.0570136070014, "count": 90, "is_parallel": true, "self": 68.6028255489997, "children": { "TorchPPOOptimizer.update": { "total": 139.4541880580017, "count": 4587, "is_parallel": true, "self": 139.4541880580017 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09700776399995448, "count": 1, "self": 0.0009162520000245422, "children": { "RLTrainer._checkpoint": { "total": 0.09609151199992993, "count": 1, "self": 0.09609151199992993 } } } } } } }