Total reward criteria for unconstrained/constrained continuous-time Markov decision processes.
Xianping GuoLanlan ZhangPublished in: J. Syst. Sci. Complex. (2011)
Keyphrases
- markov decision processes
- total reward
- state space
- stationary policies
- average reward
- optimal policy
- reinforcement learning
- reinforcement learning algorithms
- finite state
- optimality criterion
- policy iteration
- dynamic programming
- markov chain
- optimal control
- transition matrices
- decision processes
- partially observable
- markov decision process
- action space
- decision theoretic planning
- infinite horizon
- planning under uncertainty
- reward function
- stochastic processes
- average cost
- data mining
- learning algorithm