MDP based optimal control for a colloidal self-assembly system.
Yuzhen XueDaniel J. Beltran-VillegasMichael A. BevanMartha A. GroverPublished in: ACC (2013)
Keyphrases
- optimal control
- markov decision processes
- dynamic programming
- reinforcement learning
- average cost
- markov decision process
- infinite horizon
- risk sensitive
- control problems
- policy iteration
- optimal policy
- feedback control
- state space
- control strategy
- class of nonlinear systems
- markov decision problems
- brownian motion
- reward function
- partially observable
- optimal control problems
- utility function
- reinforcement learning algorithms
- control law
- finite state
- machine learning
- linear programming
- lyapunov function
- finite horizon
- initial state
- average reward
- sufficient conditions
- linear program
- stochastic control
- function approximation