Multi-stage Reinforcement Learning for Object Detection.

Jonas König Simon Malberg Martin Martens Sebastian Niehaus Artus Krohn-Grimberghe Arunselvan Ramaswamy

Published in: CVC (1) (2019)

Keyphrases

multistage
object detection
reinforcement learning
optimal policy
dynamic programming
production system
stochastic programming
lot sizing

function approximation
face detection
learning algorithm
markov decision processes
single stage
computer vision
scene understanding
multi class

state space
reinforcement learning algorithms
attack detection
optimal control
model free
stochastic optimization
object categories
pedestrian detection

machine learning
multi agent
lot streaming
infinite horizon
reward function
finite horizon
linear programming
cost function