Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
This provides theoretical foundations for understanding convergence in regularized policy iteration, addressing a gap in reinforcement learning theory, though it is incremental as it builds on existing methods.
The paper proves that regularized policy iteration in reinforcement learning is equivalent to the Newton-Raphson method under certain conditions, establishing global linear convergence with rate γ and local quadratic convergence, and shows a modified version achieves asymptotic linear convergence with rate γ^M.
Regularization is one of the most important techniques in reinforcement learning algorithms. The well-known soft actor-critic algorithm is a special case of regularized policy iteration where the regularizer is chosen as Shannon entropy. Despite some empirical success of regularized policy iteration, its theoretical underpinnings remain unclear. This paper proves that regularized policy iteration is strictly equivalent to the standard Newton-Raphson method in the condition of smoothing out Bellman equation with strongly convex functions. This equivalence lays the foundation of a unified analysis for both global and local convergence behaviors of regularized policy iteration. We prove that regularized policy iteration has global linear convergence with the rate being $γ$ (discount factor). Furthermore, this algorithm converges quadratically once it enters a local region around the optimal value. We also show that a modified version of regularized policy iteration, i.e., with finite-step policy evaluation, is equivalent to inexact Newton method where the Newton iteration formula is solved with truncated iterations. We prove that the associated algorithm achieves an asymptotic linear convergence rate of $γ^M$ in which $M$ denotes the number of steps carried out in policy evaluation. Our results take a solid step towards a better understanding of the convergence properties of regularized policy iteration algorithms.