Learning to Plan with Tree Search via Deep RL
Keywords: tree search, metareasoning, meta-level control, planning, deep reinforcement learning
TL;DR: This paper introduces a novel deep RL approach that learns how to select node expansions in planning algorithms based on tree search.
Abstract: Tree search is an important component of many decision-making algorithms but often relies on an evaluation function that estimates the desirability of each node. In this paper, we propose to learn which nodes to expand based on a variety of object-level features. We introduce a reward function for this problem based on value of computation estimates with respect to improving the policy for the underlying problem. We apply deep reinforcement learning to this problem in an approach we call Reinforcement Learning for Tree Search (RLTS) and demonstrate that it can yield better performance than baselines in a procedurally generated environment.
Submission Number: 15