{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.984488308429718, "min": 0.984488308429718, "max": 2.8591647148132324, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9399.89453125, "min": 9399.89453125, "max": 29280.70703125, "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": 12.898755073547363, "min": 0.33311203122138977, "max": 12.898755073547363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.25732421875, "min": 64.62373352050781, "max": 2615.2138671875, "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": 0.0634137687570639, "min": 0.0633980478076481, "max": 0.07537890541750719, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2536550750282556, "min": 0.2536550750282556, "max": 0.37689452708753596, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21423164236487127, "min": 0.1580648460681094, "max": 0.2885289637773645, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8569265694594851, "min": 0.6322593842724376, "max": 1.3036497211923788, "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": 25.227272727272727, "min": 3.9545454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 174.0, "max": 1420.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.9545454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 174.0, "max": 1420.0, "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": "1706850144", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706850621" }, "total": 476.6784069810001, "count": 1, "self": 0.48631101700010504, "children": { "run_training.setup": { "total": 0.05108008700000255, "count": 1, "self": 0.05108008700000255 }, "TrainerController.start_learning": { "total": 476.141015877, "count": 1, "self": 0.6213624369985951, "children": { "TrainerController._reset_env": { "total": 3.2114974520000032, "count": 1, "self": 3.2114974520000032 }, "TrainerController.advance": { "total": 472.21226226400137, "count": 18199, "self": 0.3096455660030415, "children": { "env_step": { "total": 471.9026166979983, "count": 18199, "self": 307.342698428991, "children": { "SubprocessEnvManager._take_step": { "total": 164.24410274199562, "count": 18199, "self": 1.5965746939926362, "children": { "TorchPolicy.evaluate": { "total": 162.64752804800298, "count": 18199, "self": 162.64752804800298 } } }, "workers": { "total": 0.3158155270116936, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 474.86548484400106, "count": 18199, "is_parallel": true, "self": 232.25226045899637, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007372653999993872, "count": 1, "is_parallel": true, "self": 0.0056377860000225155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017348679999713568, "count": 10, "is_parallel": true, "self": 0.0017348679999713568 } } }, "UnityEnvironment.step": { "total": 0.06724891200002503, "count": 1, "is_parallel": true, "self": 0.0006806299999766452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044889600002306906, "count": 1, "is_parallel": true, "self": 0.00044889600002306906 }, "communicator.exchange": { "total": 0.05808707700003879, "count": 1, "is_parallel": true, "self": 0.05808707700003879 }, "steps_from_proto": { "total": 0.008032308999986526, "count": 1, "is_parallel": true, "self": 0.0064173629999686455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016149460000178806, "count": 10, "is_parallel": true, "self": 0.0016149460000178806 } } } } } } }, "UnityEnvironment.step": { "total": 242.61322438500468, "count": 18198, "is_parallel": true, "self": 11.540140230000247, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8362003950073245, "count": 18198, "is_parallel": true, "self": 5.8362003950073245 }, "communicator.exchange": { "total": 188.84778769800414, "count": 18198, "is_parallel": true, "self": 188.84778769800414 }, "steps_from_proto": { "total": 36.38909606199297, "count": 18198, "is_parallel": true, "self": 6.955670421982916, "children": { "_process_rank_one_or_two_observation": { "total": 29.433425640010057, "count": 181980, "is_parallel": true, "self": 29.433425640010057 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015209200000754208, "count": 1, "self": 0.00015209200000754208, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.99451439797843, "count": 719734, "is_parallel": true, "self": 15.626921519959865, "children": { "process_trajectory": { "total": 256.3023139950188, "count": 719734, "is_parallel": true, "self": 255.78634428401887, "children": { "RLTrainer._checkpoint": { "total": 0.5159697109999115, "count": 4, "is_parallel": true, "self": 0.5159697109999115 } } }, "_update_policy": { "total": 194.0652788829998, "count": 90, "is_parallel": true, "self": 54.77379924299822, "children": { "TorchPPOOptimizer.update": { "total": 139.29147964000157, "count": 4587, "is_parallel": true, "self": 139.29147964000157 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0957416319999993, "count": 1, "self": 0.000986413000077846, "children": { "RLTrainer._checkpoint": { "total": 0.09475521899992145, "count": 1, "self": 0.09475521899992145 } } } } } } }