Text
Accelerating Primal-Dual Methods for Regularized Markov Decision Processes
Entropy regularized Markov decision processes have been widely used in reinforcement learning. This paper is concerned with the primal-dual formulation of the entropy regularized problems. Standard first-order methods suffer from slow convergence due to the lack of strict convexity and concavity. To address this issue, we first introduce a new quadratically convexified primal-dual formulation. The natural gradient ascent descent of the new formulation enjoys global convergence guarantee and exponential convergence rate. We also propose a new interpolating metric that further accelerates the convergence significantly. Numerical results are provided to demonstrate the performance of the proposed methods under multiple settings.
Barcode | Tipe Koleksi | Nomor Panggil | Lokasi | Status | |
---|---|---|---|---|---|
art148728 | null | Artikel | Gdg9-Lt3 | Tersedia namun tidak untuk dipinjamkan - No Loan |
Tidak tersedia versi lain