Action Guidance with MCTS for Deep Reinforcement Learning

Authors

  • Bilal Kartal Borealis AI
  • Pablo Hernandez-Leal Borealis AI
  • Matthew E. Taylor Borealis AI

DOI:

https://doi.org/10.1609/aiide.v15i1.5238

Abstract

Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrator to improve sample efficiency in a domain with sparse, delayed, and possibly deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. We propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with a small number rollouts, can be integrated within asynchronous distributed deep reinforcement learning methods. Compared to a vanilla deep RL algorithm, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game.

Downloads

Published

2019-10-08

How to Cite

Kartal, B., Hernandez-Leal, P., & Taylor, M. E. (2019). Action Guidance with MCTS for Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 15(1), 153-159. https://doi.org/10.1609/aiide.v15i1.5238