A First-Order Approach to Accelerated Value Iteration 1: For a Reversible Policy Chain, Accelerated Value Computation Converges at Rate 1 − √((1−λ)/(1+λ)) + η for Every η > 0Research Paper
Value iteration is the standard method for solving a discounted Markov decision process (MDP), and its policy-evaluation variant, value computation (VC), computes the value of a fixed policy by iterating an affine contraction. Both converge geometrically at rate , the discount factor. When is close to one, as in long-horizon…