Importance-Weighted Variational Inference Model Estimation for Offline Bayesian Model-Based Reinforcement Learning

This paper proposes a model estimation method in offline Bayesian model-based reinforcement learning (MBRL). Learning a Bayes-adaptive Markov decision process (BAMDP) model using standard variational inference often suffers from poor predictive performance due to covariate shift between offline data...

Descripció completa

Dades bibliogràfiques

Autors principals:	Toru Hishinuma, Kei Senda
Format:	Artigo
Idioma:	Inglês
Publicat:	IEEE 2023-01-01
Col·lecció:	IEEE Access
Matèries:	Bayesian model-based reinforcement learning decision-aware reinforcement learning offline reinforcement learning
Accés en línia:	https://ieeexplore.ieee.org/document/10368011/
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!