Risk-sensitive average continuous-time Markov decision processes with unbounded transition and cost rates.
Xin GuoYonghui HuangPublished in: J. Appl. Probab. (2021)
Keyphrases
- risk sensitive
- average cost
- markov decision processes
- optimal control
- state space
- stationary policies
- optimal policy
- finite state
- dynamic programming
- finite horizon
- infinite horizon
- reinforcement learning
- policy iteration
- control policy
- long run
- markov chain
- decision processes
- total cost
- reinforcement learning algorithms
- markov decision problems
- initial state
- state transition
- planning under uncertainty
- dynamical systems
- markov decision process
- multistage
- finite number
- average reward
- linear programming
- action space
- machine learning