Multi-agent learning, reinforcement
learning, game theory, regret-minimization, machine learning,
ad-hoc networking, text classification
I've moved to USC ISI, where I am now a Computer Scientist in the Intelligent Systems Division.
- Hedged learning: Regret minimization with learning experts. ICML '05. Joint work with Leslie Kaelbling.
- On the utility of network coding in dynamic environments. IWWAN '04. Joint work with Tracey Ho, Ben Leong, Muriel Medard, Ralf Koetter, and Michelle Effros.
- A reinforcement learning approach to mobilized ad-hoc networks. ICAC '04. Joint work with Tracey Ho and Leslie Kaelbling.
- All learning is local: Multi-agent learning in global reward games. NIPS '03. Joint work with Tracey Ho and Leslie Kaelbling.
- Text Bundling: Statistics-Based Data Reduction. ICML '03. Joint work with Kai Shih, Jason Rennie, and David Karger.
- Mobilized ad-hoc networks: A reinforcement learning approach. AI Lab Memo, 2003. Joint work with Tracey Ho and Leslie Kaelbling.
- Not Too Hot, Not Too Cold: The Bundled-SVM is Just Right! ICML '02 Text Workshop. Joint work with Kai Shih, Jason Rennie, and David Karger.
- Playing is believing: The role of beliefs in multi-agent learning. NIPS '01. Joint work with Leslie Kaelbling.