Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms,includ...
Tommi Jaakkola, Michael I. Jordan, Satinder P. Sin...
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...
While the task of answering queries from an arbitrary propositional theory is intractable in general, it can typicallybe performed e ciently if the theory is Horn. This suggests t...
We consider the problem of pricing American options when the volatility of the underlying asset price is stochastic. No specific stochastic volatility model is assumed for the st...
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...