Joseph Walton-Rivers

• Doctor of Philosophy
• Lecturer at Falmouth University

Programming concepts are challenging for new learners to grasp. This is especially the case for creative arts students who are typically unfamiliar with computing concepts and the associated vocabulary at enrolment. One means to enhance their learning is to situate examples in a relatable disciplinary context and to adapt learning material accordin...

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 th...

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 a...

Agent modelling involves considering how other agents will behave, in order to influence your own actions. In this paper, we explore the use of agent modelling in the hidden-information, collaborative card game Hanabi. We implement a number of rule-based agents, both from the literature and of our own devising, in addition to an Information Set Mon...

This document describes some of the problems encountered when trying to create believable Non-Player Characters (NPCs). It also describes the tiny coop domain and its use for testing of cooperative agents. This paper also describes the use of modelling the other agent as part of the agent's strategy and its effects for the Tiny Coop domain.

This paper highlights an experiment to see how standard Monte Carlo Tree Search handles simple cooperative problems with no prior or provided knowledge. These problems are formed from a simple grid world that has a set of goals, doors and buttons as well as walls that cannot be walked through. Two agents have to reach every goal present on the map....