Sam Devlin

Latest News

I will be giving a talk on our paper "Dynamic Potential-Based Reward Shaping" (pdf) at AAMAS 2012 on Wednesday, June 6th in Session 2C Learning II between 14:20-16:00.
I will be available for further discussion immediately afterwards at poster session 2.
For those in York, I will also be giving this talk on Wednesday, May 30th in CSE102 at 11:15.

I am involved with the following three papers to be presented at ALA 2012:

• Sam Devlin and Daniel Kudenko. Plan-Based Reward Shaping for Multi-Agent Reinforcement Learning.
• Kyriakos Efthymiadis, Sam Devlin and Daniel Kudenko. Overcoming Incorrect Knowledge in Plan-Based Reward Shaping.
• Yann-Michaël De Hauwere, Sam Devlin, Daniel Kudenko and Ann Nowé. Context Sensitive Reward Shaping in a Loosely Coupled Multi-Agent System.

They are all available in the proceedings.

About Me

I am in the final year of my studys towards a PhD degree in the Department of Computer Science at the University of York. My supervisor is Daniel Kudenko. I intend to submit in December 2012.
I am a member of the Artificial Intelligence Group. However, I am no longer organising the group's seminars. If you would like to give a talk to the group, please contact Ali Karami.

Current Research

My current research activities and interests are at the intersection of the following areas:

• Reinforcement Learning
• Multi-Agent Systems
• Reward Shaping
• (Behavioural) Game Theory

Teaching Experience

• Artificial Intelligence for Games, 2010-2012.
• Computer Science Writing, 2011.
• Introduction to Machine Learning, 2010-2012
• Introduction to Programming (Python), 2009-2011.
• Logic Programming and Artificial Intelligence, 2010.

Other Responsibilities

• Program comittee for ALA 2012
• Program committee and session chair for YDS 2011.

Publications

1. Devlin S., and Kudenko D.: Dynamic Potential-Based Reward Shaping. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2012. (Awaiting Publication) (pdf) (bib)
2. Devlin S., Grzes M., and Kudenko D.: An Empirical Study of Potential-Based Reward Shaping and Advice in Complex, Multi-Agent Systems. In Advances in Complex Systems (ACS), World Scientific Publishing Co. Pte. Ltd. (link) (pdf) (bib)
3. Devlin S., and Kudenko D.: Theoretical Considerations of Potential-Based Reward Shaping for Multi-Agent Systems. In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2011, ACM Press. (link) (pdf) (bib)
4. Devlin S., Grzes M., and Kudenko D.: Multi-Agent, Potential-Based Reward Shaping for RoboCup KeepAway (Extended Abstract) In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2011, ACM Press. (link) (pdf) (bib)
5. Devlin S., Grzes M., and Kudenko D.: Reinforcement Learning in RoboCup KeepAway with Partial Observability. In Proceedings of the IEEE/WIC/ACM International Conferences on Intelligent Agent Technology (IAT 2009), 2009. IEEE Computer Society. (link) (pdf) (bib)