TY - GEN

T1 - Hilbert space embeddings of pomdps

AU - Nishiyama, Yu

AU - Boularias, Abdeslam

AU - Gretton, Arthur

AU - Fukumizu, Kenji

PY - 2012

Y1 - 2012

N2 - A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' rule to these distribution embeddings. Policies and value functions are defined on the feature space over states, which leads to a feature space expression for the Bellman equation. Value iteration may then be used to estimate the optimal value function and associated policy. Experimental results confirm that the correct policy is learned using the feature space representation.

AB - A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' rule to these distribution embeddings. Policies and value functions are defined on the feature space over states, which leads to a feature space expression for the Bellman equation. Value iteration may then be used to estimate the optimal value function and associated policy. Experimental results confirm that the correct policy is learned using the feature space representation.

UR - http://www.scopus.com/inward/record.url?scp=84879146831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879146831&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84879146831

SN - 9780974903989

T3 - Uncertainty in Artificial Intelligence - Proceedings of the 28th Conference, UAI 2012

SP - 644

EP - 653

BT - Uncertainty in Artificial Intelligence - Proceedings of the 28th Conference, UAI 2012

T2 - 28th Conference on Uncertainty in Artificial Intelligence, UAI 2012

Y2 - 15 August 2012 through 17 August 2012

ER -