Verification of Markov Decision Processes with Risk-Sensitive Measures.
Murat CubuktepeUfuk TopcuPublished in: ACC (2018)
Keyphrases
- risk sensitive
- markov decision processes
- finite state
- dynamic programming
- optimal policy
- reinforcement learning
- state space
- average cost
- utility function
- policy iteration
- infinite horizon
- decision processes
- model free
- reinforcement learning algorithms
- optimal control
- partially observable
- action space
- planning under uncertainty
- model checking
- average reward
- finite horizon
- learning algorithm
- decision makers
- markov decision problems
- efficient optimization