Fast Regularized Policy Mirror Descent with One-Step TD Updates
Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), but existing guarantees often rely on exact or increasingly accurate policy evaluation. We analyze PMD coupled with a persistent critic advanced by one temporal-difference (TD) update. For finite discounted MDPs, we est...
Qi-Pei Chen, Wen-Ye Li, Yu-Le Sun et al.
· 0 citations