Receding horizon trajectory optimization with a finite-state value function approximation.
Bernard MettlerZhaodan KongPublished in: ACC (2008)
Keyphrases
- finite state
- markov chain
- receding horizon
- markov decision processes
- model checking
- optimal policy
- state space
- average cost
- air traffic control
- temporal difference
- policy iteration
- reinforcement learning
- partially observable markov decision processes
- optimal linear
- approximate dynamic programming
- formation control
- dynamic programming
- decision making
- machine learning