***********************************************************************************
IJCAI 2016 Workshop: Deep Reinforcement Learning: Frontiers and Challenges
New York City, New York, USA
https://sites.google.com/site/deeprlijcai16/
***********************************************************************************

IMPORTANT DATES
-----------------------------
Submission Deadline: April 20, 2016
Author Notification: May 20, 2016
Workshop: July 11, 2016

KEYNOTE SPEAKERS
-----------------------------
-Remi Munos (Google DeepMind)
-Joelle Pineau (McGill University)
-Doina Precup (McGill University)
-David Silver (Google DeepMind)
-Satinder Singh (University of Michigan)
-Peter Stone (University of Texas, Austin)

OVERVIEW
-----------------------------
There has been a resurgence of neural network models, with some additional new techniques, under the rubric of “deep learning”. Recent studies in computer vision, natural language processing, reinforcement learning, and speech recognition have amply demonstrated the potential of deep learning techniques as powerful ways of learning representations at multiple spatial and temporal scales. Reinforcement learning has traditionally used feedforward neural networks to approximate the value function, for example in the classic TD-GAMMON program in the early 1990s. Recent work by DeepMind and others have shown that deep learning techniques can enable the learning of complex tasks, such as Atari games and real-world control tasks carried out by robots. In the other direction, REINFORCE is being used in several deep learning models to learn complex tasks like image classification, and image description. It is very exciting to see that both the fields contribute to each other. In this workshop, we will focus on various ways in which representation learning, and reinforcement learning interact. This workshop will focus on Deep Reinforcement Learning, where DL is helpful in learning representations for RL, and Reinforced Deep Learning, where RL is helpful in training Deep Neural Networks. The aim of this workshop is to bring researchers from both the fields together and discuss new challenging applications which requires both Deep Learning and Reinforcement Learning.

TOPICS
-----------------------------
We are looking for contributed papers that apply Deep Learning to Reinforcement Learning and Reinforcement Learning to Deep Learning. We are interested in both application-oriented papers as well as more fundamental algorithmic/theoretical studies.

A sample list of relevant topics:
-Novel Deep Reinforcement Learning algorithms
-Deep Hierarchical Reinforcement Learning
-Reinforcement Learning for Vision/NLP
-Reinforcement Learning for training Deep Networks
-Deep Reinforcement Learning for Control
-Deep Reinforcement Learning for Robotics

SUBMISSIONS
-----------------------------
Authors should submit an extended abstract between 4 and 6 pages (including references). Submitted abstracts may be a shortened version of a longer paper or technical report, in which case the longer paper should be referred from the submission. Reviewers will be asked to judge the submission solely based on the submitted extended abstract. We also encourage submission of relevant work in progress.

All submissions must be in PDF format, and authors should follow the style guidelines of IJCAI 2016 given in: http://ijcai-16.org/downloads/FormattingGuidelinesIJCAI-16.zip

Submissions must be made through easychair: https://easychair.org/conferences/?conf=deeprl16
Submissions will be reviewed for relevance, quality and novelty. All accepted submissions will be presented as talks and/or posters at the workshop.

ORGANIZERS
-----------------------------
Sarath Chandar (anbilpas@iro.umontreal.ca)
Sridhar Mahadevan (mahadeva@cs.umass.edu)
Balaraman Ravindran (ravi@cse.iitm.ac.in)
Gerald Tesauro (gtesauro@us.ibm.com)