Performance Guarantee of an Approximate Dynamic Programming Policy for Robotic Surveillance.
Myoungkuk ParkKalyanam KrishnamoorthySwaroop DarbhaPramod P. KhargonekarMeir PachterPhillip R. ChandlerPublished in: IEEE Trans Autom. Sci. Eng. (2016)
Keyphrases
- approximate dynamic programming
- linear program
- reinforcement learning
- stochastic dynamic programming
- control policy
- dynamic programming
- actor critic
- policy iteration
- step size
- mobile robot
- average cost
- robotic systems
- optimal policy
- markov decision processes
- linear programming
- long run
- markov decision process
- control policies
- state space