An overview of coaching with limitations

Authors:
Patrick Riley;Manuela Veloso
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Year:
2003

Citing 1
Cited 2

Creating advice-taking reinforcement learners

Machine Learning - Special issue on reinforcement learning

Opponent Provocation and Behavior Classification: A Machine Learning Approach

RoboCup 2007: Robot Soccer World Cup XI
Coaching with expert system towards robocup soccer coach simulation

RoboCup 2005

Quantified Score

Hi-index	0.00

Visualization

Abstract

As agent relationships become more complex, one challenging relationship that merits study is that of coach or adviser to another agent. Our research on coaching refers to one autonomous agent providing advice to another autonomous agent about how to act. Here we describe the current state of the coach agent framework we are developing. One of our goals is to design a coach agent that can provide advice to many differently built and structured advice taking agents. A coach must then adapt its advice to the capabilities and limitations of the agents it is coaching. This paper explores the effect of advice giving in the presence of limitations.