Bayesian Inverse Reinforcement Learning for Modeling Conversational Agents in a Virtual Environment. - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

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

Abstract

This work proposes a Bayesian approach to learn the behavior of hu- man characters that give advice and help users to complete tasks in a situated environment. We apply Bayesian Inverse Reinforcement Learning (BIRL) to in- fer 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 man- ager trained to provide "locally" optimal decisions.
Fichier principal
Vignette du fichier
birl_RojasCerisara.pdf (226.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01002361 , version 1 (06-06-2014)

Identifiers

  • HAL Id : hal-01002361 , version 1

Cite

Lina Maria Rojas Barahona, Christophe Cerisara. Bayesian Inverse Reinforcement Learning for Modeling Conversational Agents in a Virtual Environment.. Conference on Intelligent Text Processing and Computational Linguistics, Alexander Gelbukh, Apr 2014, Kathmandu, Nepal. ⟨hal-01002361⟩
432 View
690 Download

Share

Gmail Facebook X LinkedIn More