Risk-Sensitive and Risk-Neutral Multiarmed Bandits.
Eric V. DenardoHaechurl ParkUriel G. RothblumPublished in: Math. Oper. Res. (2007)
Keyphrases
- risk sensitive
- risk neutral
- optimal control
- utility function
- markov decision processes
- optimality criterion
- model free
- decision theoretic
- expected utility
- control policies
- decision makers
- risk averse
- markov decision problems
- dynamic programming
- decision problems
- infinite horizon
- optimal policy
- risk aversion
- markov chain
- reinforcement learning