An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes

📖 Description

An O ine Risk-aware Policy Selection Method for Bayesian Markov Decision Processes Giorgio Angelottia,b,, Nicolas Drougarda,b, Caroline P. C. Chanela,b aANITI - Arti?cial and Natural Intelligence Toulouse Institute, University of Toulouse, France bISAE-SUPAERO, University of Toulouse, France Abstract In Oine Model Learning for Planning and in O ine Reinforcement Learning, the limited data set hinders the estimate of the Value function of the relative Markov Decision Process (MDP). Consequently, the performance of the obtained policy in the real world is bounded and possibly risky, especially when the deployment of a wrong policy can lead to catastrophic consequences. For this reason, several pathways are being followed with the scope of reducing the model error (or the distributional shift between the learned model and the true one) and, more broadly, obtaining risk-aware solutions with respect to model uncertainty. But when it comes to the ?nal application which baseline should...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/2105.13431