We study non-parametric estimation of the value function of an
infinite-...
Offline reinforcement learning, which seeks to utilize offline/historica...
We study the multi-task learning problem that aims to simultaneously ana...
We study methods based on reproducing kernel Hilbert spaces for estimati...
Point cloud upsampling aims to generate dense point clouds from given sp...
The transition kernel of a continuous-state-action Markov decision proce...
This paper considers batch Reinforcement Learning (RL) with general valu...
Bootstrapping provides a flexible and effective approach for assessing t...
This paper provides a statistical analysis of high-dimensional batch
Rei...
This paper studies the statistical theory of batch data reinforcement
le...
This paper studies how to find compact state embeddings from high-dimens...
State aggregation is a model reduction method rooted in control theory a...
This paper develops a low-nonnegative-rank approximation method to ident...