2024/03/10 by Kaiwen Wang, Dawen Liang, Wang, Kaiwen +5 · 3 citations
Computer Science · Decision Sciences · #FOS: Computer and information sciences #Formal Methods in Verification #Fuzzy Logic and Control Systems #Machine Learning (cs.LG) #Risk and Safety Analysis
paper · pdf · doi:10.48550/arxiv.2403.06323
openalex publication_date 2024/03/10 · openalex created_date 2024/03/13 · openalex updated_date 2026/07/28
We study risk-sensitive RL where the goal is learn a history-dependent policy that optimizes some risk measure of cumulative rewards. We consider a family of risks called the optimized certainty equivalents (OCE), which captures important risk measures such as conditional value-at-risk (CVaR), entropic risk and Markowitz's mean-variance. In this setting, we propose two meta-algorithms: one grounded in optimism and another based on policy gradients, both of which can leverage the broad suite of risk-neutral RL algorithms in an augmented Markov Decision Process (MDP). Via a reductions approach, we leverage theory for risk-neutral RL to establish novel OCE bounds in complex, rich-observation MDPs. For the optimism-based algorithm, we prove bounds that generalize prior results in CVaR RL and that provide the first risk-sensitive bounds for exogenous block MDPs. For the gradient-based algorithm, we establish both monotone improvement and global convergence guarantees under a discrete reward assumption. Finally, we empirically show that our algorithms learn the optimal history-dependent policy in a proof-of-concept MDP, where all Markovian policies provably fail.