Online Optimization for Offline Safe Reinforcement Learning

Yassine Chemingui (Washington State University) · Aryan Deshwal (University of Minnesota - Twin Cities) · Alan Fern (Oregon State University) · Thanh Nguyen-Tang (New Jersey Institute of Technology) · Jana Doppa (Washington State University, Pullman)

approximate optimalitycost budgetscumulative cost constraintdsrl benchmarkempirical resultsminimax objectiveno-regret online optimizationoffline policy evaluationoffline rloffline rl oracleoffline safe reinforcement learningonline optimization algorithmspractical approximationreward-maximizing policysafety constraints

We study the problem of Offline Safe Reinforcement Learning (OSRL), where the goal is to learn a reward-maximizing policy from fixed data under a cumulative cost constraint. We propose a novel OSRL approach that frames the problem as a minimax objective and solves it by combining offline RL with online optimization algorithms. We prove the approximate optimality of this approach when integrated with an approximate offline RL oracle and no-regret online optimization. We also present a practical approximation that can be combined with any offline RL algorithm, eliminating the need for offline policy evaluation. Empirical results on the DSRL benchmark demonstrate that our method reliably enforces safety constraints under stringent cost budgets, while achieving high rewards. The code is available at https://github.com/yassineCh/O3SRL.