The Limits and Robustness of Reinforcement Learning in Lewis Signaling Games

TitleThe Limits and Robustness of Reinforcement Learning in Lewis Signaling Games
Publication TypeJournal Article
Year of Publication2014
AuthorsCatteeuw, D, Manderick, B
JournalConnection Science
Volume26
Issue2
Start Page161
Pagination177
ISSN0954-0091
Keywordslewis signaling games, reinforcement learning, signaling, win-stay/lose-inaction
Abstract

Lewis signalling games are a standard model to study the emergence of language. We introduce win-stay/lose-inaction, a random process that only updates behaviour on success and never deviates from what was once successful, prove that it always ends up in a state of optimal communication in all Lewis signalling games, and predict the number of interactions it needs to do so: N^3 interactions for Lewis signalling games with N equiprobable types. We show three reinforcement learning algorithms (Roth–Erev learning, Q-learning, and Learning Automata) that can imitate win-stay/lose-inaction and can even cope with errors in Lewis signalling games.

 

DOI10.1080/09540091.2014.885303