Saturday, 26 October

8:00 Breakfast

Session 4 (8:30am-10:30am), McDonnell A02, Chair: Doina Precup

8:30-9:20 Michael Littman – Computational game theory in sequential environments
9:20-9:55 Anne Churchland – Linking circuits to behavior in visual decision making
9:55-10:30 Elke Weber – An idiosyncratic history of RLDM

10:30-11:00 Coffee break

Session 5 (11:00am-1:05pm), McDonnell A02, Chair: Peter Dayan

11:00-11:35 Nathaniel Daw – Model based and model free reinforcement learning in the brain
11:35-11:55 Peter Smittenaar*, Thomas FitzGerald, George Prichard, Vincenzo Romei, Nicholas Wright, Joern Diedrichsen & Raymond Dolan – Manipulating model-based and model-free control through neurostimulation of prefrontal cortex (Best Paper Award)
11:55-12:30 Stefan Schaal – Perception, action, learning and associative skill memories
12:30-1:05 John O’Doherty – The role of ventrolateral prefrontal cortex in the arbitration between model-based and model-free reinforcement-learning

1:05-2:30 Lunch sponsored by Lockheed Martin, Frick main foyer

2:00-2:30 NSF outreach session, Frick B02 – NSF funding possibilities for RLDM research (Donald Hantula & Akaysha Tang)

Session 6 (2:30pm-4:35pm), McDonnell A02, Chair: Joelle Pineau

2:30-3:05 Craig Boutillier – Preference elicitation for social choice: A study in stable matching and voting
3:05-3:40 Jonathan Cohen – Toward a rational understanding of the capacity constraints in cognitive control
3:40-4:15 Drew Bagnell – Rich Sutton was right: Provably good RL via online learning
4:15-4:35 Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles Isbell & Andrea Thomaz* – Policy shaping: Integrating human feedback with reinforcement learning

4:35-7:30 Posters, wine & tea (posters available till midnight), Frick foyer

Dinner on your own (list of local restaurants here)