Bayesian Inverse Reinforcement Learning for Modeling Conversational Agents in a Virtual Environment

Autor:	Christophe Cerisara, Lina M. Rojas-Barahona
Rok vydání:	2014
Předmět:	business.industry Computer science Bayesian probability Context (language use) computer.software_genre Machine learning Virtual machine Inverse reinforcement learning Markov decision process Artificial intelligence Baseline (configuration management) business computer Advice (complexity)
Zdroj:	Computational Linguistics and Intelligent Text Processing ISBN: 9783642549052 CICLing (1)
Popis:	This work proposes a Bayesian approach to learn the behavior of human characters that give advice and help users to complete tasks in a situated environment. We apply Bayesian Inverse Reinforcement Learning BIRL to infer this behavior in the context of a serious game, given evidence in the form of stored dialogues provided by experts who play the role of several conversational agents in the game. We show that the proposed approach converges relatively quickly and that it outperforms two baseline systems, including a dialogue manager trained to provide "locally" optimal decisions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::70a88fd83d814ef995c10d59b13b87a4 https://doi.org/10.1007/978-3-642-54906-9_41 Zobrazit plný text záznamu