University of Hertfordshire

By the same authors

Accelerating Empowerment Computation with UCT Tree Search

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations
Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Conference on Computational Intelligence and Games, CIG 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781538643594
Publication statusPublished - 15 Oct 2018
Event14th IEEE Conference on Computational Intelligence and Games, CIG 2018 - Maastricht, Netherlands
Duration: 14 Aug 201817 Aug 2018


Conference14th IEEE Conference on Computational Intelligence and Games, CIG 2018


Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from intrinsically motivated general game-playing agents to non-player characters such as companions and enemies. The information-theoretic quantity of Empowerment is a particularly promising candidate motivation to produce believable, generic and robust behaviour. However, while it can be used in the absence of external reward functions that would need to be crafted and learned, empowerment is computationally expensive. In this paper, we propose a modified UCT tree search method to mitigate empowerment's computational complexity in discrete and deterministic scenarios. We demonstrate how to modify a Monte-Carlo Search Tree with UCT to realise empowerment maximisation, and discuss three additional modifications that facilitate better sampling. We evaluate the approach both quantitatively, by analysing how close our approach gets to the baseline of exhaustive empowerment computation with varying amounts of computational resources, and qualitatively, by analysing the resulting behaviour in a Minecraft-like scenario.

ID: 16383330