A Learning Algorithm for Risk-Sensitive Cost 

 - Bangalore:  Department of Mathematics, Indian Institute of Science:  2006 
 - A linear function approximation based reinforcement learning algorithm is proposed for Markov decision processes with infinite horizon risk-sensitive cost. Its convergence is proved using the ‘o.d.e. method’ for stochastic approximation. The scheme is als 
<br/><br/><label>ISBN: </label>NULL