Biography

Hi, I'm Joseph Walton-Rivers. I'm a lecturer at Falmouth University. My work focuses on artificial intelligence for games, focusing on believability and non-player characters. I run the Hanabi competition, aimed at creating co-operative agents for partially observable card games at CIG for the the past two years. He spends his free time providing programming support and technical consultancy to Nysko Games, a games company created by former students at the University of Essex.

Website

Featured Research

Distributed Social Multi-Agent Negotiation Framework For Incomplete Information Games

In this paper, we propose a social negotiation system in which agents can communicate and interact with each other socially throughout a Sheriff of Nottingham game. We address issues with the number of options available while negotiating, particularly when bluffing is involved. Experiments are proposed that would allow us to validate how closely this framework mirrors real social interaction in the game, and the possibility of generalising multi-agent negotiation beyond this framework is raised.

The 2018 Hanabi competition

This paper outlines the Hanabi competition, first run at CIG 2018, and returning for COG 2019. Hanabi presents a useful domain for game agents which must function in a cooperative environment. The paper presents the results of the two tracks which formed the 2018 competition and introduces the learning track, a new track for 2019 which allows the agents to collect statistics across multiple games.

Hexboard: A generic game framework for turn-based strategy games

In this paper we outline our game framework, Hexboard, and its possible applications for games research. We outline the architecture of the game framework and the reasons for our design choices. We present games created in the framework, both by ourselves and students enrolled on a game design course. We found that a wide variety of interesting games could be made with the Hexboard framework with relative ease. Finally, we outline future work for this framework and some possible uses for it within games research.