top of page
Abstraction in RL
ICML WORKSHOP 2016
New York,
23rd June 2016
INVITED TALKS
Pieter Abeel: Deep Reinforcement Learning for Robotics
(Slides)
George Konidaris: Combining State and Temporal Abstraction (Slides)
Doina Precup/Pierre-Luc Bacon: Advances in Option Construction: The option-critic architecture (Slides)
David Silver: Mastering the game of Go with Deep Neural Networks and Tree Search (Slides)
Aviv Tamar: Value Iteration Networks (Slides)
Emma Brunskill: Towards Representation for Efficient Reinforcement Learning (Slides)
ORAL PRESENTATIONS
Workshop by Daniel J. Mankowitz, Timothy A. Mann and Shie Mannor: Introduction (Slides)
Emmanuel Bengio et al.: Reinforcement Learning of Conditional Computation Policies for Neural Networks (Slides)
Tejas Kulkarni et al.: Deep Reinforcement Learning with Temporal Abstraction and Intrinsic Motivation (Slides)
David Abel et al.: Gradient Boosting for Reinforcement Learning in Complex Domains (Slides)
Sponsored by:
bottom of page