Heuristic Search Based Exploration in Reinforcement Learning

Ngo Anh Vien, Nguyen Hoang Viet, SeungGwan Lee, TaeChoong Chung

Abstract

In this paper, we consider reinforcement learning in systems with unknown environment where the agent must trade off efficiently between: exploration(long-term optimization) and exploitation (short-term optimization). ε− greedy algorithm is a method using near-greedy action selection rule. It behaves greedily (exploitation) most of the time, but every once in a while, say with small probability ε (exploration), instead select an action at random. Many works already proved that random exploration drives the agent towards poorly modeled states. Therefore, this study evaluates the role of heuristic based exploration in reinforcement learning. We proposed three methods: neighborhood search based exploration, simulated annealing based exploration, and tabu search based exploration. All techniques follow the same rule ”Explore the most unvisited state”. In the simulation, these techniques are evaluated and compared on a discrete reinforcement learning task (robot navigation).
BibTeX
@inproceedings{vien2007heuristic,
  author = {Ngo Anh Vien and Nguyen Hoang Viet and SeungGwan Lee and TaeChoong Chung},
  title = {{Heuristic Search Based Exploration in Reinforcement Learning}},
  booktitle = {IWANN},
  year = {2007},
  doi = {10.1007/978-3-540-73007-1\_14},
}

Loading related content...

Figure