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

Lina Maria Rojas Barahona 1 Christophe Cerisara 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01002361
Contributor : Lina Maria Rojas Barahona <>
Submitted on : Friday, June 6, 2014 - 9:08:48 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:01 PM
Document(s) archivé(s) le : Saturday, September 6, 2014 - 11:06:18 AM

File

birl_RojasCerisara.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01002361, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

636

Files downloads

615