Risk-sensitive continuous-time Markov decision processes with unbounded rates and Borel spaces.
Xianping GuoJunyu ZhangPublished in: Discret. Event Dyn. Syst. (2019)
Keyphrases
- markov decision processes
- risk sensitive
- state space
- stationary policies
- dynamic programming
- optimal control
- finite state
- optimal policy
- markov chain
- policy iteration
- average cost
- infinite horizon
- reinforcement learning
- reinforcement learning algorithms
- finite horizon
- action space
- action sets
- planning under uncertainty
- decision processes
- average reward
- partially observable
- partially observable markov decision processes
- markov decision process
- dynamical systems
- state variables
- multistage
- learning algorithm