New prioritized value iteration for Markov decision processes
نویسندگان
چکیده
منابع مشابه
Interactive Value Iteration for Markov Decision Processes with Unknown Rewards
To tackle the potentially hard task of defining the reward function in a Markov Decision Process, we propose a new approach, based on Value Iteration, which interweaves the elicitation and optimization phases. We assume that rewards whose numeric values are unknown can only be ordered, and that a tutor is present to help comparing sequences of rewards. We first show how the set of possible rewa...
متن کاملFast Value Iteration for Goal-Directed Markov Decision Processes
P lanning problems where effects of actions are non-deterministic can be modeled a8 Markov decision processes. Planning prob lems are usually goal-directed. This paper proposes several techniques for exploiting the goal-directedness to accelerate value itera tion, a standard algorithm for solving Markov decision processes. Empirical studies have shown that the techniques can bring about signi...
متن کاملApproximate Value Iteration for Risk-aware Markov Decision Processes
We consider large-scale Markov decision processes (MDPs) with a risk measure of variability in cost, under the risk-aware MDPs paradigm. Previous studies showed that risk-aware MDPs, based on a minimax approach to handling the risk measure, can be solved using dynamic programming for small to medium sized problems. However, due to the “curse of dimensionality”, MDPs that model real-life problem...
متن کاملTopological Value Iteration Algorithm for Markov Decision Processes
Value Iteration is an inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, which turns out to be unnecessary in many cases. In order to overcome this problem, many approaches have been proposed. Among them, LAO*, LRTDP and HDP are state-of-theart ones. All of these use reachability analysis and heuristics t...
متن کاملOnline Markov decision processes with policy iteration
The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and theoretically establish a sublinear regret bound. A notable advantage of the proposed algorithm is that it can be easily combined with function approximation, and thu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Artificial Intelligence Review
سال: 2011
ISSN: 0269-2821,1573-7462
DOI: 10.1007/s10462-011-9224-z