kyriakos.efthymiadis

My current research interests and activities are within the context of the following areas :

• Reinforcement Learning
• Knowledge, Belief Revision
• Planning
• RL for games

Teaching

Teaching Assistant:

• Logic Programming and Artificial Intelligence, (2nd year UG module, 2010-2011)

Reading List

Books:

• Russell, S. J., Norvig, P., Canny, J. F., Malik, J. M., & Edwards, D. D. (1995). Artificial intelligence: a modern approach (Vol. 2). Englewood Cliffs, NJ: Prentice hall.
• Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction (Vol. 1, No. 1). Cambridge, MA: MIT press.
• Wiering, M., & van Otterlo, M. (Eds.). (2012). Reinforcement Learning: State-of-the-Art (Vol. 12). Springer.
• Ghallab, M., Nau, D., & Traverso, P. (2004). Automated Planning: Theory & Practice. Morgan Kaufmann.
• Gardenfors, P. (Ed.). (2003). Belief revision (Vol. 29). Cambridge University Press.

Papers:

• Randlov, J., & Alstrom, P. (1998, July). Learning to drive a bicycle using reinforcement learning and shaping. In Proceedings of the Fifteenth International Conference on Machine Learning (pp. 463-471).
• Ng, A. Y., Harada, D., & Russell, S. (1999, June). Policy invariance under reward transformations: Theory and application to reward shaping. In Machine Learning-International Workshop then Conference - (pp. 278-287). Morgan Kaufmann Publishers, Inc.
• Wiewiora, E., Cottrell, G., & Elkan, C. (2003). Principled methods for advising reinforcement learning agents. In Machine Learning-International Workshop then Conference - (Vol. 20, No. 2, p. 792).
• Wiewiora, E. (2003). Potential-based shaping and Q-value initialization are equivalent. J. Artif. Intell. Res. (JAIR), 19, 205-208.
• Devlin, S., & Kudenko, D. (2012, June). Dynamic potential-based reward shaping. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1 (pp. 433-440). International Foundation for Autonomous Agents and Multiagent Systems.
• Grzes, M., & Kudenko, D. (2008, September). Plan-based reward shaping for reinforcement learning. In Intelligent Systems, 2008. IS'08. 4th International IEEE Conference (Vol. 2, pp. 10-22). IEEE.