{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.974486231803894, "min": 0.974486231803894, "max": 2.8657336235046387, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9336.552734375, "min": 9336.552734375, "max": 29411.0234375, "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": 12.342032432556152, "min": 0.35241949558258057, "max": 12.342032432556152, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2406.6962890625, "min": 68.369384765625, "max": 2481.345703125, "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.Environment.CumulativeReward.mean": { "value": 24.704545454545453, "min": 3.477272727272727, "max": 24.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1087.0, "min": 153.0, "max": 1351.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.704545454545453, "min": 3.477272727272727, "max": 24.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1087.0, "min": 153.0, "max": 1351.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07113881957169117, "min": 0.06274146055682864, "max": 0.07494897813744858, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2845552782867647, "min": 0.25096584222731455, "max": 0.37287962123189256, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18944861067860735, "min": 0.12386798256706885, "max": 0.27545347914976237, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7577944427144294, "min": 0.4954719302682754, "max": 1.3772673957488117, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029184900271699997, "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": 0.19728300000000004, "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": 0.0048644217, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "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": "1679830251", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679830856" }, "total": 604.0923880720001, "count": 1, "self": 0.5925703709999652, "children": { "run_training.setup": { "total": 0.13554485800000293, "count": 1, "self": 0.13554485800000293 }, "TrainerController.start_learning": { "total": 603.3642728430001, "count": 1, "self": 0.8794790199920044, "children": { "TrainerController._reset_env": { "total": 7.1141263199999685, "count": 1, "self": 7.1141263199999685 }, "TrainerController.advance": { "total": 595.2123622680082, "count": 18204, "self": 0.463740429007089, "children": { "env_step": { "total": 594.7486218390011, "count": 18204, "self": 478.22026647897565, "children": { "SubprocessEnvManager._take_step": { "total": 116.10711015701531, "count": 18204, "self": 3.347268108024082, "children": { "TorchPolicy.evaluate": { "total": 112.75984204899123, "count": 18204, "self": 112.75984204899123 } } }, "workers": { "total": 0.42124520301013035, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 601.005759104999, "count": 18204, "is_parallel": true, "self": 265.99731075799593, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007329570000024432, "count": 1, "is_parallel": true, "self": 0.004543495999882907, "children": { "_process_rank_one_or_two_observation": { "total": 0.002786074000141525, "count": 10, "is_parallel": true, "self": 0.002786074000141525 } } }, "UnityEnvironment.step": { "total": 0.041934557999979916, "count": 1, "is_parallel": true, "self": 0.0006841479997774513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030385700006263505, "count": 1, "is_parallel": true, "self": 0.00030385700006263505 }, "communicator.exchange": { "total": 0.03870181800004957, "count": 1, "is_parallel": true, "self": 0.03870181800004957 }, "steps_from_proto": { "total": 0.002244735000090259, "count": 1, "is_parallel": true, "self": 0.00046523499986506067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017795000002251982, "count": 10, "is_parallel": true, "self": 0.0017795000002251982 } } } } } } }, "UnityEnvironment.step": { "total": 335.0084483470031, "count": 18203, "is_parallel": true, "self": 13.919644676994267, "children": { "UnityEnvironment._generate_step_input": { "total": 7.544915995999304, "count": 18203, "is_parallel": true, "self": 7.544915995999304 }, "communicator.exchange": { "total": 268.16701480100994, "count": 18203, "is_parallel": true, "self": 268.16701480100994 }, "steps_from_proto": { "total": 45.37687287299957, "count": 18203, "is_parallel": true, "self": 9.428728843958083, "children": { "_process_rank_one_or_two_observation": { "total": 35.94814402904149, "count": 182030, "is_parallel": true, "self": 35.94814402904149 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018465699986336404, "count": 1, "self": 0.00018465699986336404, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 590.0530862379886, "count": 594923, "is_parallel": true, "self": 14.989465029985354, "children": { "process_trajectory": { "total": 320.783296517003, "count": 594923, "is_parallel": true, "self": 319.378295071003, "children": { "RLTrainer._checkpoint": { "total": 1.4050014460000284, "count": 4, "is_parallel": true, "self": 1.4050014460000284 } } }, "_update_policy": { "total": 254.28032469100026, "count": 90, "is_parallel": true, "self": 88.59249956000144, "children": { "TorchPPOOptimizer.update": { "total": 165.68782513099882, "count": 4587, "is_parallel": true, "self": 165.68782513099882 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15812057800008006, "count": 1, "self": 0.0012159710001924395, "children": { "RLTrainer._checkpoint": { "total": 0.15690460699988762, "count": 1, "self": 0.15690460699988762 } } } } } } }