Learning trading negotiations using manually and automatically labelled data

Heriberto Cuayahuitl, Simon Keizer, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Strategic conversational agents often need to trade resources with their opponent conversants - and trading strategically can lead to better results. While rule-based or supervised agents can be used for such a purpose, here we explore a learning approach based on automatically labelled examples from human players for automatic trading in the game of Settlers of Catan. Our experiments are based on data collected from human players trading in text-based natural language. We compare the performance of Bayes Nets, Conditional Random Fields, and Random Forests on the task of ranking trading offers, trained from both manually labelled and automatically labelled data. Our experimental results show that our best agent trained on automatic labels outperformed its counterpart trained on manual labels (with moderate annotator agreement) in terms of (a) predicting human trading negotiations better, and (b) winning more games.

Original languageEnglish
Title of host publication2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI)
PublisherIEEE
Pages904-911
Number of pages8
ISBN (Print)9781509001637
DOIs
Publication statusPublished - 2015
Event27th IEEE International Conference on Tools with Artificial Intelligence 2015 - Vietri sul Mare, Salerno, Italy
Duration: 9 Nov 201511 Nov 2015

Conference

Conference27th IEEE International Conference on Tools with Artificial Intelligence 2015
Abbreviated titleICTAI 2015
CountryItaly
CityVietri sul Mare, Salerno
Period9/11/1511/11/15

Keywords

  • Automatic labelling
  • Board games
  • Semi-supervised learning
  • Strategic interaction
  • Supervised learning

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Learning trading negotiations using manually and automatically labelled data'. Together they form a unique fingerprint.

Cite this