Back from ArgMAS in Toronto; a nice and interesting trip! I have put online both my paper and presentation for anyone to download it.
Eric M. Kok, John-Jules Ch. Meyer, Henry Prakken, and Gerard A. W. Vreeswijk. A Formal Argumentation Framework for Deliberation Dialogues. Proceedings of the 7th International Workshop on Argumentation in Multi-Agent Systems. Toronto (Canada), 2010 [Abstract] [Full paper] [Presentation]
This month I started my new job as a PhD student at the Intelligent Systems group at the Utrecht University. I will be working on the NWO-funded project ‘Agents Interacting in Dialogues with Argumentation’, or AIDA. We will try to prove if and how the use of argumentation in agent to agent dialogue can be beneficial and how this is measured. My main supervisor is Prof. Mr. Dr. Henry Prakken.
Last month I graduated for my masters in Agent Technology at the Utrecht University. I received a mark of 8,5 out of 10 for my master thesis project ‘Adaptive reinforcement learning agents in real-time strategy games‘. Thanks again to my supervisors Frank Dignum and Joost Westra. I have always found it very interesting and challenging to work on the intelligent agents for games. Hopefully, someone will continue on my work.
I’m currently busy with my Master’s degree graduation project on machine learning in computer games. This video shows some preliminary work on learning a counter-strategy in the Bos Wars RTS game using 2apl.
For my study I did an experimentation project on learning in agent environments. The idea is to build action selection learning into the 2APL agent platform. It uses different reinforcement learning techniques to allow software agents to learn what actions give the best result while trying to reach a goal.
The full report can be downloaded and describes how it was implemented and what RL methods worked best in a random gridworld environment searching for bombs.
After the ‘Can computers be creative?’ presentation, I’ve also written an essay on the topic. Available for download!
Last Monday I gave a presentation on the philosophical subject ‘Can computers be creative?’. Everything went well and the discussion was lively. The PowerPoint presentation can be download here. It covers topics like the definition of creativity and if artificial creativity can be build in principle and it shows some practical research projects done on this subject.
A very interesting and accessible discussion transcript between Kurtzweil, Gelernter and Brooks can be found at KurtzweilAI.net: “Will machine become consciousness?”.
Well, we’ve managed to get the poker player to learn, finally. Just in time for the project ending.
It’s available under GPL at the SourceForge website of RL Poker or directly download the .jar files. To run, read the instructions on the release system page.
For my master study Agent Technology at the Utrecht University, I was part of a little group making a learning poker player:
RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold’em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.
Have a look at the SourceForge project website. Code is available from SVN.