We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in complex domains such as RoboCup soccer, and show how to use automatically generated advice to perform transfer. Categories and Subject Descriptors I.2 [Artificial Intelligence]: Learning General Terms Algorithms, Experimentation Keywords Advice, Knowledge Transfer, Reinforcement Learning 							
						
							
					 															
					Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa