A mean-variance optimization problem for discounted Markov decision processes.
Xianping GuoLiuer YeGeorge YinPublished in: Eur. J. Oper. Res. (2012)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- transition matrices
- infinite horizon
- reinforcement learning
- dynamic programming
- decision theoretic planning
- policy iteration
- average reward
- finite horizon
- average cost
- partially observable
- factored mdps
- reinforcement learning algorithms
- planning under uncertainty
- reachability analysis
- decision processes
- markov decision process
- utility function
- action space
- risk sensitive
- action sets
- discounted reward
- machine learning
- discount factor
- model based reinforcement learning
- reward function
- total reward
- decision making