Search Machine Learning Repository:
Scaling Up Robust MDPs using Function Approximation
Authors: Aviv Tamar, Shie Mannor and Huan Xu
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handling uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimensionality", MDPs that model real-life problems are typically prohibitively large for such approaches. In this work we employ a reinforcement learning approach to tackle this planning problem: we develop a robust approximate dynamic programming method based on a projected fixed point equation to approximately solve large scale robust MDPs. We show that the proposed method provably succeeds under certain technical conditions, and demonstrate its effectiveness through simulation of an option pricing problem. To the best of our knowledge, this is the first attempt to scale up the robust MDP paradigm.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).