Connectionists: WCCI2016 Special Session on: Deep Reinforcement Learning

[Abdulrahman Altahhan]

Dear All,

We are organizing a special session in the ranked A conference of IJCNN(International Joint Conference of Neural Networks), the call can be found below. I would like to encourage relevant work to be submitted to this important venue.

The World Congress on Computational Intelligence (WCCI2016)

July 25-29, 2016

Special Session (IJCNN 44)

“Deep and Reinforcement Learning Models”
Deep Learning has been under the focus of neural network research and industrial communities due to its proven ability to scale well into difficult problems and due to its performance breakthroughs over other architectural and learning techniques in important benchmarking problems. This was mainly in the form of improved data representation in supervised learning tasks. On the other hand, Reinforcement learning (RL) is considered the model of choice for problems that involve learning from interaction, where the target is to optimize a long term control strategy or to learn to formulate an optimal policy. Typically these applications involve processing a stream of data coming from different sources, ranging from central massive databases to pervasive smart sensors.
Open-questions
RL does not lend itself naturally to deep learning and currently there is no uniformed approach to combine deep learning with reinforcement learning despite good attempts. Examples of important open questions are: How to make the state-action learning process deep? And how to make the architecture of an RL system appropriate to deep learning without compromising the interactivity of the system? Although recently there have been important advances in dealing with these issues, they are still scattered and with no overarching framework that promote them in a well-defined and natural way.
Aim and objectives
This special session aims at providing a unique platform for researchers from Deep Learning and Reinforcement Learning communities to share their research experience towards a unified Deep Reinforcement Learning (DRL) framework in order to allow this important interdisciplinary branch to take-off on solid grounds. In addition to the above open-questions, fundamental questions are bound to be addressed; for example the benefits and drawbacks of methods to combine RL and DL, or how deep DL can be infused into RL? While at the other end, pragmatic questions should be addressed; for example how to harmonize both frameworks to effectively serve on-line big and streamed action data processing application?
Contribution is invited for deep learning, reinforcement learning and deep reinforcement learning models.

Scope and topics

1.      Novel Deep and RL Neural Architectures

2.      Adaptation of existing RL Techniques for Deep Learning

3.      Optimization and convergence proofs for DRL algorithms

4.      Deeply Hierarchical RL

5.      Deep and/or RL architecture and algorithms for Control

6.      Deep and/or RL architecture and algorithms for Robotics

7.      Deep and/or RL architecture and algorithms for Time Series

8.      Deep and/or RL architecture and algorithms for Big Streamed Data Processing

9.      Deep and/or RL architecture and algorithms for Optimizing Governmental Policy

10.   Other Deep and/or RL applications

Paper submission:
Potential authors may submit their manuscripts for presentation consideration through WCCI2016 submission system. All the submissions will go through peer review. Details on manuscript submission can be found from http://www.wcci2016.org/submission.php
Important dates:

·         Paper submission deadline:                                                                       January 31, 2016

·         Notification of acceptance:                                                                        March 15, 2016

·         Final paper submission and early registration deadline:              April 15, 2016
Thank you in advance for your participation
Yours sincerely,
Abdulrahman Altahhan, Coventry University, UK, ab8556 at coventry.ac.uk<mailto:ab8556 at coventry.ac.uk>

Vasile Palade, Coventry University, UK, vpalade453 at gmail.com<mailto:vpalade453 at gmail.com>


_______________________________
Dr Abdulrahman Altahhan
Lecturer in Computer Science
Course Director for MSc in Data Science
School of Computing, Electronics and Maths
Faculty of Engineering and Computing
Coventry University,
Coventry CV1 5FB
+44 (0) 2477653088
Room EC4 22


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20160115/881ab7f4/attachment.html>