2013/06/26 by Aviv Tamar, Huan Xu, Tamar, Aviv +3 · 4 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.1306.6189
openalex publication_date 2013/06/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 handle 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 MDPs paradigm.