The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
The Web contains an abundance of useful semistructured information about real world objects, and our empirical study shows that strong sequence characteristics exist for Web infor...
Jun Zhu, Zaiqing Nie, Ji-Rong Wen, Bo Zhang, Wei-Y...
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficul...