Planning for the Real World:
The promises and challenges of dealing with uncertainty

Tentative Schedule:

7:30-8:15 Introduction to planning under uncertainty, Michael Littman, Rutgers University

8:15-8:45 Predictive models for reinforcement learning, Satinder Singh, University of Michigan

8:45-9:00 Risk, Reward and Reinforcement, John Moody, ICSI

9:00-9:15 Break

9:15-9:45 Reasoning about uncertainty due to external agents, Geoff Gordon, Carnegie Mellon University

9:45-10:15 (Im)Practical reinforcement learning theory, John Langford, Toyota Technological Institute at Chicago

10:15-10:30 Discussion

Afternoon Session:

4:00-4:30 Learning Control and Planning from the View of Control Theory and Imitation, Jan Peters and Stefan Schaal, University of Southern California

4:30-4:45 Poster Spotlights

4:45-5:45 Poster Session

5:45-6:00 Break

6:00-6:30 Apprenticeship learning, Andrew Ng, Stanford University

6:30-7:00 Wrap-up / Discussion

Poster presentations:

• Pieter Abbeel and Andrew Ng: "Apprenticeship Learning via Inverse Reinforcement Learning"
  
• Allison Bruce: "Decision Theoretic Approaches to Human-Robot Social Interaction"
  
• Rosemary Emery-Montemerlo: "Approximate Solutions for Partially Observable Stochastic Games"
  
• Milos Hauskrecht and Branislav Kveton: "Linear Program Approximations for Factored Continuous-State Markov Decision Processes"
  
• Brendan McMahan and Geoff Gordon: "Planning in Cost-Paired Markov Decision Process Games"
  
• Jan Peters, Sethu Vijayakumar and Stefan Schaal: "Natural Actor Critic"
  
• Kurt Steinkraus and Leslie Pack Kaelbling: "Combining dynamic abstractions in very large MDPs"
  
• Alberto Reyes, L. Enrique Sucar, Eduardo Morales, and Pablo Ibarguengotia: "Relational MDPs using Qualitative Proportionality Predicates: An Application in Power Generation"
  
• Nikos Vlassis and Matthijs Spaan: "A fast point-based algorithm for POMDPs"
  

Main Page
Schedule
Call for Posters

CONTACT: