DR-PETS: Learning-Based Control With Planning in Adversarial Environments
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Control Systems Letters"
DOI: 10.1109/lcsys.2025.3587053
Abstract: The probabilistic ensembles with trajectory sampling (PETS) algorithm is a recognized baseline among model-based reinforcement learning (MBRL) methods. PETS incorporates planning and handles uncertainty using ensemble-based probabilistic models. However, no formal robustness guarantees against epistemic… read more here.
Keywords: control; pets learning; learning based; based control ... See more keywords