Login / Signup
Small Parameter Limit for Ergodic, Discrete-Time, Partially Observed, Risk-Sensitive Control Problems.
Francesca Albertini
Paolo Dai Pra
Chiara Prior
Published in:
Math. Control. Signals Syst. (2001)
Keyphrases
</>
control problems
optimal control
risk sensitive
partially observed
markov chain
dynamic programming
reinforcement learning
infinite horizon
control strategy
control law
real time
average cost
learning algorithm
optimal solution
utility function