Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management.
Tomasz R. BieleckiDaniel Hernández-HernándezStanley R. PliskaPublished in: Math. Methods Oper. Res. (1999)
Keyphrases
- finite state
- markov chain
- risk sensitive
- portfolio management
- optimal control
- markov decision processes
- average cost
- markov decision chains
- steady state
- state space
- control policies
- optimal policy
- monte carlo
- transition probabilities
- portfolio selection
- markov model
- random walk
- utility function
- stationary distribution
- control policy
- markov processes
- reinforcement learning
- portfolio optimization
- markov decision problems
- partially observable markov decision processes
- policy iteration
- dynamic programming
- hidden markov models
- control system
- infinite horizon