Risk-Averse Learning by Temporal Difference Methods with Markov Risk Measures
We propose a novel reinforcement learning methodology where the system performance is evaluated by a Markov coherent dynamic risk measure with the use of linear value function approximations. We construct projected risk-averse dynamic programming equations and study their properties. We propose new risk-averse counterparts of the basic and multi-step methods of temporal differences and we prove their convergence with probability one. We also perform an empirical study on a complex transportation problem.