Risk-Sensitive Discounted Continuous-Time Markov Decision Processes with Unbounded Rates.
Xianping GuoZhong-Wei LiaoPublished in: SIAM J. Control. Optim. (2019)
Keyphrases
- markov decision processes
- risk sensitive
- state space
- optimal policy
- stationary policies
- optimal control
- average cost
- finite state
- reinforcement learning
- infinite horizon
- dynamic programming
- markov chain
- policy iteration
- finite horizon
- reinforcement learning algorithms
- average reward
- decision problems
- markov decision process
- action space
- discounted reward
- partially observable
- dynamical systems
- search algorithm
- planning under uncertainty
- multi agent
- machine learning