A Note on the Reward Function for PHD Filters with Sensor Control.

Branko Ristic Ba-Ngu Vo Daniel E. Clark

Published in: IEEE Trans. Aerosp. Electron. Syst. (2011)

Keyphrases

reward function
control system
markov decision processes
multiple agents
state space
reinforcement learning
reinforcement learning algorithms
control policies
inverse reinforcement learning
decision makers
optimal policy
autonomous robots