The 2nd Asian Workshop on

Reinforcement Learning (AWRL’17)

November 15, 2017, Yonsei University, Seoul, Korea

In conjunction with the 9th Asian Conference on Machine Learning (ACML 2017)

Previous Workshops:

 

Sponsors:

LAMDA Group, 

National Key Laboratory for Novel Software Technology,

Nanjing University (China)

Keynote Speaker 

Thomas G. Dietterich, Oregon State University, USA 

Invited Speakers  

Mohammad Ghavamzadeh, Google Deepmind, USA 

Wee Sun Lee, National University of Singapore 

Bruno Scherrer, INRIA, France 

Songhwai Oh, Seoul National University, South Korea  

Program (Room 3)

08:00 Registration Open
08:30-08:35 Introduction
08:35-09:25 Invited Talk 1: Sparse Markov Decision Processes
Songhwai Oh (Seoul National University, South Korea)
09:25-09:55 Session 1 (25m + 5m questions)
Haiyan Yin and Sinno Jialin Pan. Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay (AAAI’17)
09:55-10:10 Break
10:10-11:00 Invited Talk 2: Learning Safe Policies in Sequential Decision-Making
Mohammad Ghavamzadeh (Google Deepmind, USA)
11:00-11:30 Session 2 (25m + 5m questions)
Jongmin Lee, Youngsoo Jang, Pascal Poupart and Kee-Eung Kim. Constrained Bayesian Reinforcement Learning via Approximate Linear Programming (IJCAI’17)
11:30-12:30 Lunch
12:30-13:20 Keynote: Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning.
Thomas G. Dietterich (Oregon State University, USA)
13:20-14:10 Invited Talk 3: Approximation Algorithms for Interactive Learning and Planning
Wee Sun Lee (National University of Singapore, Singapore)
14:10-15:00 Invited Talk 4: Two Simple Tricks for Improving the Solution to Large RL Problems
Bruno Scherrer (INRIA, France)
15:00-15:30 Session 3 (25m + 5m questions)
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt and Marcus Hutter. Count-Based Exploration in Feature Space for Reinforcement Learning (IJCAI’17)

Motivation

The Asian Workshop on Reinforcement Learning (AWRL) focuses on both theoretical foundations, models, algorithms, and practical applications. In the last few years, we have seen a growing interest in RL of researchers from different research areas and industries. We invite reinforcement learning researchers and practitioners to participate in this world-class gathering. We intend to make this an exciting event for researchers and practitioners in RL worldwide, not only for the presentation of top quality papers, but also as a forum for the discussion of open problems, future research directions and application domains of RL. 

AWRL 2017 (in conjunction with ACML 2017) will consist of keynote talks, contributed paper presentations, and discussion sessions spread over a one-day period.

Topics 

The workshop will cover a range of sub-topics in RL, from theoretical aspects to empirical evaluations, including but not limited to:

  • ◦ Exploration/Exploitation
  • ◦ Function approximation in RL
  • ◦ Deep RL
  • ◦ Policy search methods
  • ◦ Batch RL
  • ◦ Kernel methods for RL
  • ◦ Evolutionary RL
  • ◦ Partially observable RL
  • ◦ Bayesian RL
  • ◦ Multi-agent RL
  • ◦ RL in non-stationary domains
  • ◦ Life-long RL
  • ◦ Non-standard Criteria in RL, e.g.:
    • ◦ Risk-sensitive RL
    • ◦ Multi-objective RL
    • ◦ Preference-based RL
  • ◦ Transfer Learning in RL
  • ◦ Knowledge Representation in RL
  • ◦ Hierarchical RL
  • ◦ Interactive RL
  • ◦ RL in psychology and neuroscience
  • ◦ Applications of RL, e.g.:
    • ◦ Recommender systems
    • ◦ Robotics
    • ◦ Video games
    • ◦ Finance

Paper Submission 

AWRL is a non-archival venue and there will be NO published proceedings. However, the papers will be posted on this website. Therefore it will be possible to submit to other conferences and journals both in parallel to and after AWRL 2017. Besides, we also welcome submissions to AWRL that are under review at other conferences and workshops. For this reason, please feel free to submit either anonymized or non-anonymized versions of your work. We have enabled anonymous reviewing so EasyChair will not reveal the authors unless you chose to do so in your PDF.

At least one author from each accepted paper must register for the workshop. Please see the ACML 2017 Website for information about accommodation and registration.

Papers are recommended to be formatted according to the ACML formatting instructions for the Conference Track. Submissions need not be anonymous.

Workshop submissions and camera ready versions will be handled by EasyChair. Click here for submission.

Important Dates 

    •    Submission deadline: 10 Aug. 2017    27 Aug. 2017

    •    Notification of acceptance: 10 Sep. 2017

    •    Online camera-ready: 10 Oct. 2017

    •    Workshop date: 15 Nov. 2017

    •    ACML dates: 15-17 Nov. 2017

Organizing Committee (in alphabetic order)

Tao Qin, Microsoft Research Asia

Paul Weng, SYSU-CMU Joint Institute of Engineering, China

Yang Yu, Nanjing University, China

Zongzhang Zhang, Soochow University, China