Model-Free Grasp Planning for Configurable Vacuum Grippers.

Fang You Michael Mende Denis Stogl Björn Hein Torsten Kröger

Published in: IROS (2018)

Keyphrases

model free
reinforcement learning
reinforcement learning algorithms
function approximation
policy iteration
temporal difference
planning problems
policy evaluation
state space
pattern recognition
planning domains
average reward