9:00 - 9:45 Rich Sutton - Planning in RL
9:45 -10:30 Byron Boots - Hilbert Space Embeddings of Predictive State Representations
10:30 -11:00 Break
11:00 -11:45 Erik Talvitie - Learning to make predictions in high-dimensional, partially observable domains
11:45 -12:15 Scott Sanner -Symbolic Dynamic Programming for Hybrid MDPs
12:15 -12:45 Marc Bellemare - Pixels and Priors: Learning a Generative Model of Atari 2600 Games
Evening:
7:00 - 8:00 Mausam and Andrey Kolobov -- An Overview of MDP Planning Research at ICAPS [Lecture Room]
8:10 - 9:30 Discussion on Representations for Planning led by Scott Sanner & Michael Littman [Dinnner Area]
Monday, April 29
Morning:
Temporal abstraction
9:00 - 9:30 Doina Precup - Planning to explore using options
9:30 - 10:00 Dave Silver - Compositional Planning Using Optimal Option Models
10:00 -10:30 Tom Schaul - Better generalization with forecasts
10:30 -11 Break
Guiding search
11:00 -11:30 Tobias Jung - Optimized Lookahead Tree Policies: A Bridge Between Lookahead Tree Policies and Direct Policy Search
11:30 -12:00 Harm van Seijen - Efficient Prioritized Sweeping with Exact Bellman Error Ordering
12:00 -12:30 Csaba Szepesvari - Optimistic optimization algorithms for planning in MDPs I
12:30 - 1:00 Andras Gyorgy - Optimistic optimization algorithms for planning in MDPs II
Evening:
7:00 - 7:30 Elliot Ludvig - Making decisions by replaying the past
7:30 - 8:15 John O’Doherty - Neural correlates of arbitration between model-based and model-free reinforcement-learning
8:15 - 8:30 Break
8:30 - 9:00 Matt Botvinick - Optimal behavioral hierarchy
9:00 - 9:30 Yuan Chang - Learning what’s relevant in a largely irrelevant world: The role of selective attention in representation learnings
Tuesday, April 30
Morning:
POMDPs & Traditonal Planning
9:00 - 9:30 Richard Dearden - Replanning in POMDPs in Response to Unexpected Events
9:30 - 10:00 Pascal Poupart - Constrained POMDPs
10:00 - 10:30 Dan Weld - Specifying Adaptive Programs – a Challenge for RL
10:30 - 11:00 Break
11:00 - 11:30 Subramanian Ramamoorthy - Clustering Markov Decision Processes for a Lifelong Learning Agent
11:30 - 12:00 Mausam - Automatic Basis Function Construction for Goal-directed MDPs
12:00 - 12:30 Andrey Kolobov - Pitfalls of Goal-Oriented Planning Under Uncertainty
Evening:
7:00-9:30 Break-out Group Discussions
Morning:
Applications
9:00 - 9:30 Joseph Modayil - Planning with learned models on robots
9:30 - 10:00 Patrick Pilarski - Real-time Control with Temporally Extended Predictions: A Sensorimotor Approach to Planning?
10:00 - 10:30 Wouter Caarls - Parallel DYNA
10:30 - 11:00 Break
11:00 -11:30 Michael Bowling - Arcade Learning Environment
11:30 -12:00 Samuel Barrett - Planning to Cooperate with Unknown Teammates
12:00 -12:30 Russ Greiner - Learning to help patients manage diabetes
