Mean-semivariance optimality for continuous-time Markov decision processes.
Qingda WeiPublished in: Syst. Control. Lett. (2019)
Keyphrases
- markov decision processes
- stationary policies
- average cost
- state space
- average reward
- action sets
- optimal policy
- finite state
- policy iteration
- dynamic programming
- optimal control
- reinforcement learning
- transition matrices
- markov chain
- markov decision process
- planning under uncertainty
- reachability analysis
- decision processes
- decision theoretic planning
- partially observable
- infinite horizon
- action space
- risk sensitive
- optimal solution
- sufficient conditions
- state and action spaces
- factored mdps
- reinforcement learning algorithms
- state abstraction
- dynamical systems
- finite horizon
- semi markov decision processes
- model based reinforcement learning
- linear program
- lot sizing
- initial state