Program

Monday:

Opening session (19h00) (30min talk + 30min discussion):
Chair: Satinder Singh
19h00-20h00: Welcome and two views of planning Richard Sutton 
20h00-21h00: Use a model if you have it! Russ Tedrake

21h00-22h00: The system must have a life...and relations Martijn van Otterlo 


Tuesday:

Views of Model Based Reinforcement Learning (09h00):
Chair: Richard Sutton

09h00-09h40: Using hierarchical Bayes to learn models and plan in them David Wingate (30min talk)

09h40-10h20: Lifted reasoning (for RL and beyond) Geoff Gordon (30min talk)

      plus Geoff recommends this tutorial on lifted probabilistic representations by David Poole.
 10h20-10h40: Break


10h40-11h00: Temporal Abstractions for Knowledge Representation (Anna Koop) (20min talk)

11h00-11h20: Modeling the world with multi-layer predictrons (David Silver) (20min talk)
11h20-11h40: Break




12h20-13h00: Planning with an untrustworthy model Michael Bowling (30min talk)




Evening (19h00):

Chair: Doina Precup
  9h40-20h20: Do animals learn models of their environment Elliot Ludvig (30min talk)
20h20-20h40: Break
20h40-21h20: Cognitive neuroscience and goal-directed (read model-based decision making Matthew Botvinick (30min talk)
19h00-19h30: Where do rewards come from? Richard Lewis (30min talk)

21h20-22h00: Open Discussion



Wednesday:



Planning (9h00)
:
Chair: Michael Bowling
09h00-09h40: Planning and RL: A tale of two worlds Prasad Tadepalli (30min talk)

09h40-10h00: Learning and planning with partial models (Neville Mehta) (20min talk)
10h00-10h20: Optimistic planning of deterministic systems (Jean-François Hren) (20min talk)

10h20-10h40: Discussion


10h40-11h00: Break



Chair: Martijn van Otterlo
Planning:
11h00-11h40: Random thoughts  Csaba Szepesvári (30min talk)
11h40-12h00: Fitted Natural Actor-Critic: A new algorithm for continuous state-action MDPs (Francisco Melo) (20min talk)

Representations:
12h00-12h20: Embedding 101: Reconstructing nonlinear dynamical systems from time series data (Jordan Frank)
12h20-12h40: Manifold Embeddings for Reinforcement Learning with Partial Observability (Keith Bush)
12h40-13h00: Discussion

Evening (19h00-22h00):
Open discussion



Thursday:



Temporal abstraction (09h00):
Chair: Prasad Tadepalli

09h00-09h40: Doina Precup (30min talk)

09h40-10h10: Linear Option Models (Jonathan Sorg) (20min talk)
10h10-10h40: Optimal Policy Switching Algorithms (Gheorghe Comanici) (20min talk)


10h40-10h50: Break



Model learning:
Chair: Csaba Szepesvári
10h50-11h20: Tools for learning RL representations (Carlos Diuk) (20min talk)
11h20-11h50: Gradient-descent methods for temporal difference learning with linear function approximation (Hamid Maei) (20min talk)
11h50-12h20: Transfer Learning in Related Reinforcement Learning Tasks (Alessandro Lazaric) (20min talk)
12h20-12h50: Model learning in strongly structured environments (Gabor Bartok) (20min talk)



Evening:
Strategies for progress (19h00):


Chair: Dale Schuurmans
19h00-19h20: 
Critterbot (Thomas Degris-Dard) (20min talk)
19h20-19h40: 
The RLAI Robotic Simulator (Marc Bellemare) (20min talk)
19h40-20h00:  Discussion

20h00-20h30: RL Community Tools State of the Union AND A Trail Towards More General Empirical Reinforcement Learning (Brian Tanner)
20h30-22h00: Discussion



Friday:



Representations (9h00):
Chair: David Wingate
09h00-09h20: Generalized Model Learning in Reinforcement Learning (Todd Hester) (20min talk)
09h20-09h40: Model-based Bayesian Reinforcement Learning with Adaptive State Aggregation (Cosmin Paduraru) (20min talk)
09h40-10h00: Discussion

10h00-10h30: Break

Chair: Geoff Gordon
10h30-11h00: Learning Approximate Representations of Partially Observable Systems (Monica Dinculescu) (20min talk)
11h00-11h30: OOMs, PSRs, S-MAs and a statistically efficient learning algorithm (Michael Thon) (20min talk)
11h30-12h00: Maintaining the values of predictive features without a model (Erik Talvitie)

 (20min talk)
12h00-12h30: Error-Bars for Bayesian Net Inference (Yasin Abbasi) (20min talk)


Ċ
Richard Sutton,
Apr 16, 2009, 8:35 AM
Ċ
Richard Sutton,
Apr 17, 2009, 9:26 PM
Ċ
Richard Sutton,
Apr 16, 2009, 10:05 PM
Ċ
Richard Sutton,
Apr 17, 2009, 8:58 PM
Ċ
Richard Sutton,
Apr 16, 2009, 8:30 AM
Ċ
bushTalk.pdf
(4467k)
Richard Sutton,
Apr 18, 2009, 3:08 PM
Ċ
Thomas Degris-Dard,
Apr 17, 2009, 11:06 AM
Ċ
Richard Sutton,
Apr 20, 2009, 9:45 AM
Ċ
Richard Sutton,
Apr 16, 2009, 9:51 PM
Ċ
Richard Sutton,
Apr 15, 2009, 9:17 PM
Ċ
Richard Sutton,
Apr 16, 2009, 10:04 PM
Ċ
Richard Sutton,
Apr 20, 2009, 9:46 AM
Ċ
Richard Sutton,
Apr 17, 2009, 8:58 PM
Ċ
Richard Sutton,
Apr 17, 2009, 8:58 PM
Ċ
Richard Sutton,
Apr 16, 2009, 10:03 PM
Ċ
Richard Sutton,
Apr 16, 2009, 10:05 PM
Ċ
maeiTalk.pdf
(2401k)
Richard Sutton,
Apr 18, 2009, 3:08 PM
Ċ
Richard Sutton,
Apr 15, 2009, 9:12 PM
Ċ
meloTalk.pdf
(5346k)
Richard Sutton,
Apr 16, 2009, 8:32 AM
Ċ
Richard Sutton,
Apr 18, 2009, 3:07 PM
Ċ
Richard Sutton,
Apr 14, 2009, 2:06 PM
Ċ
Richard Sutton,
Apr 15, 2009, 9:14 PM
Ċ
Richard Sutton,
Apr 16, 2009, 8:34 AM
Ċ
Richard Sutton,
Apr 18, 2009, 3:07 PM
Ċ
Richard Sutton,
Apr 15, 2009, 9:38 PM
Ċ
Richard Sutton,
Apr 20, 2009, 9:45 AM
Ċ
Richard Sutton,
Apr 15, 2009, 9:25 PM
Ċ
Richard Sutton,
Apr 16, 2009, 8:31 AM
Comments