Paper Info
Title
Reinforcement learning and optimal adaptive control: An overview and implementation examples.
Abstract
This paper provides an overview of the reinforcement learning and optimal adaptive control literature and its application to robotics. Reinforcement learning is bridging the gap between traditional optimal control, adaptive control and bio-inspired learning techniques borrowed from animals. This work is highlighting some of the key techniques presented by well known researchers from the combined areas of reinforcement learning and optimal control theory. At the end, an example of an implementation of a novel model-free Q-learning based discrete optimal adaptive controller for a humanoid robot arm is presented. The controller uses a novel adaptive dynamic programming (ADP) reinforcement learning (RL) approach to develop an optimal policy on-line. The RL joint space tracking controller was implemented for two links (shoulder flexion and elbow flexion joints) of the arm of the humanoid Bristol-Elumotion-Robotic-Torso II (BERT II) torso. The constrained case (joint limits) of the RL scheme was tested for a single link (elbow flexion) of the BERT II arm by modifying the cost function to deal with the extra nonlinearity due to the joint constraints.
Year
DOI
Venue
2012
10.1016/j.arcontrol.2012.03.004
Annual Reviews in Control
Keywords
Field
DocType
Reinforcement learning,ADP,Q-learning,Optimal adaptive control
Control theory,Optimal control,Control theory,Joint constraints,Q-learning,Control engineering,Artificial intelligence,Adaptive control,Engineering,Robotics,Humanoid robot,Reinforcement learning
Journal
Volume
Issue
ISSN
36
1
1367-5788
Citations 
PageRank 
References 
37
1.46
59
Authors
5
Name
Order
Citations
PageRank
Said Ghani Khan1716.71
Guido Herrmann28311.31
FRANK L. LEWIS35782402.68
Tony Pipe417124.02
Chris Melhuish574787.61