Accelerating Empowerment Computation with UCT Tree Search

Salge, Christoph; Guckelsberger, Christian; Canaan, Rodrigo and Mahlmann, Tobias. 2018. 'Accelerating Empowerment Computation with UCT Tree Search'. In: Computational Intelligence and Games. Maastricht, Netherlands 14-17 August 2018. [Conference or Workshop Item]

[img]
Preview
Text
Salge_Accelerating_Empowerment_With_UTC_Tree_Search.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (288kB) | Preview
Official URL: http://www.ieee-cig.org/

Abstract or Description

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.

Item Type:

Conference or Workshop Item (Paper)

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
30 April 2018Accepted
14 August 2018Published

Event Location:

Maastricht, Netherlands

Date range:

14-17 August 2018

Item ID:

23415

Date Deposited:

12 Jun 2018 13:55

Last Modified:

14 Jun 2021 23:10

URI:

https://research.gold.ac.uk/id/eprint/23415

View statistics for this item...

Edit Record Edit Record (login required)