When modeling real-world decision-theoretic planning problems in the Markov decision process (MDP) framework, it is often impossible to obtain a completely accurate estimate of tr...
Karina Valdivia Delgado, Scott Sanner, Leliane Nun...
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
The problem of completing a low-rank matrix from a subset of its entries is often encountered in the analysis of incomplete data sets exhibiting an underlying factor model with app...