Redundancy Resolution as Action Bias in Policy Search for Robotic Manipulation.

Firas Al-Hafez Jochen J. Steil

Published in: CoRL (2021)

Keyphrases

policy search
continuous action
reinforcement learning
robotic systems
continuous state
mobile robot
reinforcement learning algorithms
dynamic programming
function approximation
policy gradient
reward function
markov decision problems
random walk
autonomous robots