Tackling Sparse Rewards in Real-Time Games with Statistical Forward Planning Methods

Authors

  • Raluca D. Gaina Queen Mary University of London
  • Simon M. Lucas Queen Mary University of London
  • Diego Pérez-Liébana Queen Mary University of London

DOI:

https://doi.org/10.1609/aaai.v33i01.33011691

Abstract

One of the issues general AI game players are required to deal with is the different reward systems in the variety of games they are expected to be able to play at a high level. Some games may present plentiful rewards which the agents can use to guide their search for the best solution, whereas others feature sparse reward landscapes that provide little information to the agents. The work presented in this paper focuses on the latter case, which most agents struggle with. Thus, modifications are proposed for two algorithms, Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms, aiming at improving performance in this type of games while maintaining overall win rate across those where rewards are plentiful. Results show that longer rollouts and individual lengths, either fixed or responsive to changes in fitness landscape features, lead to a boost of performance in the games during testing without being detrimental to non-sparse reward scenarios.

Downloads

Published

2019-07-17

How to Cite

Gaina, R. D., Lucas, S. M., & Pérez-Liébana, D. (2019). Tackling Sparse Rewards in Real-Time Games with Statistical Forward Planning Methods. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1691-1698. https://doi.org/10.1609/aaai.v33i01.33011691

Issue

Section

AAAI Technical Track: Game Playing and Interactive Entertainment