Constrained Offline Policy Optimization
Abstract
In this work we introduce Constrained Offline Policy Optimization (COPO), an offline policy optimization algorithm for learning in MDPs with cost constraints. COPO is built upon a novel offline cost-projection method, which we formally derive and analyze. Our method improves upon the state-of-the-art in offline constrained policy optimization by explicitly accounting for distributional shift and by offering non-asymptotic confidence bounds on the cost of a policy. These formal properties are superior to those of existing techniques, which only guarantee convergence to a point estimate. We formally analyze our method and empirically demonstrate that it achieves state-of-the-art performance on discrete and continuous control problems, while offering the aforementioned improved, stronger, and more robust theoretical guarantees.