{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.893731951713562, "min": 0.8917700052261353, "max": 2.8464105129241943, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8562.845703125, "min": 8562.845703125, "max": 29212.7109375, "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": 12.633474349975586, "min": 0.24414430558681488, "max": 12.633474349975586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2463.527587890625, "min": 47.36399459838867, "max": 2538.966796875, "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": 0.06581398020738133, "min": 0.060001738162770615, "max": 0.07307168837852421, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632559208295253, "min": 0.24549910227149524, "max": 0.36337753862208755, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1804840759757687, "min": 0.11914424927603892, "max": 0.2871132452113956, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7219363039030748, "min": 0.4765769971041557, "max": 1.3001098968819076, "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": 25.272727272727273, "min": 3.1363636363636362, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 138.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.1363636363636362, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 138.0, "max": 1370.0, "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": "1691754047", "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": "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": "1691754557" }, "total": 510.138579983, "count": 1, "self": 0.4343038499999352, "children": { "run_training.setup": { "total": 0.04777910400002838, "count": 1, "self": 0.04777910400002838 }, "TrainerController.start_learning": { "total": 509.65649702900004, "count": 1, "self": 0.6162003570099159, "children": { "TrainerController._reset_env": { "total": 5.380950310999992, "count": 1, "self": 5.380950310999992 }, "TrainerController.advance": { "total": 503.51576461499013, "count": 18204, "self": 0.30937718798497826, "children": { "env_step": { "total": 503.20638742700515, "count": 18204, "self": 366.0540421690119, "children": { "SubprocessEnvManager._take_step": { "total": 136.8414783180055, "count": 18204, "self": 2.070649118007111, "children": { "TorchPolicy.evaluate": { "total": 134.7708291999984, "count": 18204, "self": 134.7708291999984 } } }, "workers": { "total": 0.31086693998776127, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 507.85990384399895, "count": 18204, "is_parallel": true, "self": 239.9653875409955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006273668000005728, "count": 1, "is_parallel": true, "self": 0.004746518999922955, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015271490000827725, "count": 10, "is_parallel": true, "self": 0.0015271490000827725 } } }, "UnityEnvironment.step": { "total": 0.06555639100002963, "count": 1, "is_parallel": true, "self": 0.000585731000001033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042164500001717897, "count": 1, "is_parallel": true, "self": 0.00042164500001717897 }, "communicator.exchange": { "total": 0.062293781000050785, "count": 1, "is_parallel": true, "self": 0.062293781000050785 }, "steps_from_proto": { "total": 0.0022552339999606374, "count": 1, "is_parallel": true, "self": 0.0004149190001498937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018403149998107438, "count": 10, "is_parallel": true, "self": 0.0018403149998107438 } } } } } } }, "UnityEnvironment.step": { "total": 267.89451630300346, "count": 18203, "is_parallel": true, "self": 11.252337360014394, "children": { "UnityEnvironment._generate_step_input": { "total": 5.737733321997894, "count": 18203, "is_parallel": true, "self": 5.737733321997894 }, "communicator.exchange": { "total": 211.03919091499478, "count": 18203, "is_parallel": true, "self": 211.03919091499478 }, "steps_from_proto": { "total": 39.86525470599639, "count": 18203, "is_parallel": true, "self": 7.433420284014346, "children": { "_process_rank_one_or_two_observation": { "total": 32.431834421982046, "count": 182030, "is_parallel": true, "self": 32.431834421982046 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017250799999146693, "count": 1, "self": 0.00017250799999146693, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 499.4523900899649, "count": 478482, "is_parallel": true, "self": 11.06095389795803, "children": { "process_trajectory": { "total": 275.6396203400063, "count": 478482, "is_parallel": true, "self": 274.7794526320063, "children": { "RLTrainer._checkpoint": { "total": 0.860167707999949, "count": 4, "is_parallel": true, "self": 0.860167707999949 } } }, "_update_policy": { "total": 212.75181585200062, "count": 90, "is_parallel": true, "self": 83.48828438200349, "children": { "TorchPPOOptimizer.update": { "total": 129.26353146999713, "count": 4587, "is_parallel": true, "self": 129.26353146999713 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14340923800000382, "count": 1, "self": 0.0008406219999415043, "children": { "RLTrainer._checkpoint": { "total": 0.14256861600006232, "count": 1, "self": 0.14256861600006232 } } } } } } }