Pattern control for networks of Ginzburg-Landau oscillators via Markov Decision Processes.
Airlie ChapmanEric SchoofMehran MesbahiPublished in: CDC (2016)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- decision theoretic planning
- transition matrices
- reinforcement learning
- decentralized control
- policy iteration
- model based reinforcement learning
- reinforcement learning algorithms
- planning under uncertainty
- dynamic programming
- reachability analysis
- action space
- finite horizon
- monte carlo
- markov decision process
- control system
- factored mdps
- state and action spaces
- optimal control
- semi markov decision processes
- control problems
- average cost
- infinite horizon
- search space
- model checking
- linear programming
- data mining