Skip to content. | Skip to navigation

Personal tools
Log in
Sections
You are here: Home Papers Constrained Bayesian Reinforcement Learning via Approximate Linear Programming

Jongmin Lee, Youngsoo Jang, Pascal Poupart, and Kee-Eung Kim (2017)

Constrained Bayesian Reinforcement Learning via Approximate Linear Programming

In: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI).

In this paper, we consider the safe learning scenario where we need to restrict the exploratory behavior of a reinforcement learning agent. Specifically, we treat the problem as a form of Bayesian reinforcement learning in an environment that is modeled as a constrained MDP (CMDP) where the cost function penalizes undesirable situations. We propose a model-based Bayesian reinforcement learning (BRL) algorithm for such an environment, eliciting risk-sensitive exploration in a principled way. Our algorithm efficiently solves the constrained BRL problem by approximate linear programming, and generates a finite state controller in an offline manner. We provide theoretical guarantees and demonstrate empirically that our approach outperforms the state of the art.