Programme

 Time Event Title
09:00 - 09:05 Introductory Remarks: Sridhar Mahadevan  
09:05 - 09:35 Invited Talk: Satinder SinghRecent Results in Deep RL for Games 
09:35 - 10:00 Contributed Spotlights - I  
10:00 - 10:30 Invited Talk: Remi Munos Off-policy return-based RL 
10:30 - 11:00 Tea Break  
11:00 - 11:30 Invited Talk: Doina Precup RL-Deep: Using RL tricks to address open problems in deep learning
11:30 - 11:55 Contributed Spotlights - II 
11:55 - 12:25 Invited Talk: Peter Stone Deep Multiagent RL for Partially Observable Parameterized Environments 
12:25 - 01:30Lunch Break  
01:30 - 02:00 Invited Talk: David SilverDeep Reinforcement Learning
02:00 - 02:30 Invited Talk: Joelle Pineau Natural Language Processing: Challenges and Opportunities for Deep RL 
02:30 - 03:00 Invited Talk: Pieter Abbeel Deep Reinforcement Learning for Robotics 
03:00 - 04:00Poster Session  
04:00 - 04:20 DLAI Workshop Summary: David W. Aha  
04:20 - 05:30 Panel Discussion Deep RL: Frontiers and Challenges
Panelists: Joelle Pineau, Satinder Singh, David Silver, Gerry Tesauro


Contributed Spotlights - I 
  1. Classifying Options for Deep Reinforcement Learning. Kai Arulkumaran, Nat Dilokthanakul, Murray Shanahan and Anil A. Bharath.
  2. Model-based Reinforcement Learning with Neural Networks on Hierarchical Dynamic System. Akihiko Yamaguchi and Christopher Atkeson.
  3. A Deep Hierarchical Approach to Lifelong Learning in Minecraft. Chen Tessler, Shahar Givony, Tom Zahavy, Daniel J Mankowitz and Shie Mannor.
  4. Data-Efficient Deep Reinforcement Learning with Bayesian Neural Network Dynamics Models. Yarin Gal, Rowan McAllister and Carl Rasmussen.
  5. Deep Reinforcement Learning in a 3-D Blockworld Environment. Trevor Barron, Matthew Whitehead and Alan Yeung.
  6. Dynamic Frame skip Deep Q Network. Aravind Srinivas Lakshminarayanan, Sahil Sharma and Balaraman Ravindran.
Contributed Spotlights - 2 
  1. Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks. Jakob Foerster, Yannis Assael, Nando de Freitas and Shimon Whiteson.
  2. Initial Progress in Transfer for Deep Reinforcement Learning Algorithms. Yunshu Du, Gabriel de La Cruz, James Irwin and Matthew Taylor.
  3. On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning. Matthew Hausknecht and Peter Stone.
  4. Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes. Caglar Gulcehre, Sarath Chandar, Kyunghyun Cho and Yoshua Bengio.
  5. Perceptual Reward Functions. Ashley Edwards, Charles Isbell and Atsuo Takanishi.

Comments