Close menu


Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Support Rather Than Assault – Cooperative Agents in Minecraft

Potts, Danielle, MacFarlane, Kate and Hall, Lynne (2021) Support Rather Than Assault – Cooperative Agents in Minecraft. In: 33rd British Computer Society Human Computer Interaction conference, 19-21 July 2021, Online.

Item Type: Conference or Workshop Item (Paper)


With the dominant trope of the computer as adversary rather than enabler, reinforcement learning for games has mainly focused on the ability of agents to compete and win. Although cooperation is a product of learning, of understanding the player’s requirements and applying agents’ competences to fulfil them, there has been little investigation of reinforcement learning for cooperation in games. Reinforcement learning results in the agent adapting and changing, however, there are concerns that such adaptivity could alienate users if their cooperative agent outperforms them. To explore this, the paper outlines the development and training of cooperative agents reporting users’ positive response to adaptive cooperation in games.

Potts-MacFarlane-Hall Position paper BHCI.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

Download (127kB) | Preview

More Information

Related URLs:
Depositing User: Lynne Hall


Item ID: 13659
Official URL:

Users with ORCIDS

ORCID for Kate MacFarlane: ORCID iD
ORCID for Lynne Hall: ORCID iD

Catalogue record

Date Deposited: 13 Jul 2021 15:27
Last Modified: 24 Jan 2023 10:01


Author: Kate MacFarlane ORCID iD
Author: Lynne Hall ORCID iD
Author: Danielle Potts

University Divisions

Faculty of Technology > School of Computer Science


Computing > Artificial Intelligence
Computing > Games Design
Computing > Human-Computer Interaction

Actions (login required)

View Item View Item