Robust Modified Policy Iteration

A Unified Approach to Algorithms with a Suboptimality Test in Discounted Semi-markov Decision Processes

This paper deals with computational algorithms for obtaining the optimal stationary policy and the minimum cost of a discounted semi-Markov decision process. Van Nunen [23) has proposed a modified policy iteration algorithm with a suboptimality test of MacQueen type, where the modified policy iteration algorithm is policy iteration method with the policy evaluation routine by a finite number of...

Non-Stationary Approximate Modified Policy Iteration

We consider the infinite-horizon γ-discounted optimal control problem formalized by Markov Decision Processes. Running any instance of Modified Policy Iteration—a family of algorithms that can interpolate between Value and Policy Iteration—with an error at each iteration is known to lead to stationary policies that are at least 2γ (1−γ)2 -optimal. Variations of Value and Policy Iteration, that ...

Modified Halpern Iteration of Asymptotically Non-Expansive Mappings

Learning Robust Options

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally abstract actions, in the framework of options. We present a Robust Options Po...

Accelerating of Modified Policy Iteration in Probabilistic Model Checking

Markov Decision Processes (MDPs) are used to model both non-deterministic and probabilistic systems. Probabilistic model checking is an approach for verifying quantitative properties of probabilistic systems that are modeled by MDPs. Value and Policy Iteration and modified version of them are well-known approaches for computing a wide range of probabilistic properties. This paper tries to impro...