We propose a provably correct Monte Carlo tree search (MCTS) algorithm for solving risk-aware Markov decision processes (MDPs) with entropic risk measure (ERM) objectives. We provide a non-asymptotic analysis of our proposed algorithm, showing that the algorithm: (i) is correct in the sense that the empirical ERM obtained at the root node converges to the optimal ERM; and (ii) enjoys polynomial regret concentration. Our algorithm successfully exploits the dynamic programming formulations for solving risk-aware MDPs with ERM objectives introduced by previous works in the context of an upper confidence bound-based tree search algorithm. Finally, we provide a set of illustrative experiments comparing our risk-aware MCTS method against relevant baselines.
@article{arxiv.2601.17667,
title = {Entropic Risk-Aware Monte Carlo Tree Search},
author = {Pedro P. Santos and Jacopo Silvestrin and Alberto Sardinha and Francisco S. Melo},
journal= {arXiv preprint arXiv:2601.17667},
year = {2026}
}