We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
To gain insights into the neural basis of such adaptive decision-making processes, we investigated the nature of learning process in humans playing a competitive game with binary ...
Abstract--The H.264 standard achieves much higher coding efficiency than the MPEG-2 standard, due to its improved inter-and intra-prediction modes at the expense of higher computat...
The decision tree is one of the most fundamental ing abstractions. A commonly used type of decision tree is the alphabetic binary tree, which uses (without loss of generality) &quo...