We investigate the problem of minimizing the Average-Value-at-Risk (AVaR <Subscript> τ </Subscript>) of the discounted cost over a finite and an infinite horizon which is generated by a Markov Decision Process (MDP). We show that this problem can be reduced to an ordinary MDP with extended state space and give...</subscript>

We investigate the problem of minimizing the Average-Value-at-Risk (AVaR τ ) of the discounted cost over a finite and an infinite horizon which is generated by a Markov Decision Process (MDP). We show that this problem can be reduced to an ordinary MDP with extended state space and give...