Is human-like and well playing contradictory for Diplomacy bots?

This paper presents a nonplayer character (NPC, bot) for the strategy game Diplomacy. The bot is able to communicate with other players and thus shows a human-like behavior. We investigate how far the playing abilities can be improved without corrupting the human-like behavior. Is there a trade-off...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE Symposium on Computational Intelligence and Games pp. 209 - 216
Main Authors Kemmerling, M., Ackermann, N., Beume, N., Preuss, M., Uellenbeck, S., Walz, W.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2009
Subjects
Automatic testing
Humans
Monitoring
Online AccessGet full text

Cover

More Information
Summary:This paper presents a nonplayer character (NPC, bot) for the strategy game Diplomacy. The bot is able to communicate with other players and thus shows a human-like behavior. We investigate how far the playing abilities can be improved without corrupting the human-like behavior. Is there a trade-off at all or do these skills complement one another? Different versions of the bot are tested against other bots and humans which requires means to automatically measure believability. We derive such a measure after a general approach and apply it for monitoring the believability criterion while improving the playing strength of our bot.
ISBN:9781424448142
142444814X
ISSN:2325-4270
DOI:10.1109/CIG.2009.5286472