Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes.
Stefano P. CoraluppiSteven I. MarcusPublished in: Autom. (1999)
Keyphrases
- markov decision processes
- finite state
- risk sensitive
- optimal policy
- average cost
- state space
- dynamic programming
- reinforcement learning
- markov decision chains
- markov decision process
- planning under uncertainty
- optimal control
- infinite horizon
- control policies
- policy iteration
- finite horizon
- average reward
- control policy
- partially observable
- reinforcement learning algorithms
- control system
- partially observable markov decision processes
- control strategy
- markov chain
- action sets