SURL 2017 - 1st Scaling-Up Reinforcement Learning Workshop (SURL)

1st Scaling-Up Reinforcement Learning Workshop (SURL)
Held during ECML PKDD-17
Skopje -- Macedonia
September 18th
http://www.surl.tirl.info
===
Important Dates
===
Paper Submission Deadline: July 3rd, 2017
Notification to authors: July 24th, 2017
Final Version Deadline: August 7th, 2017
Motivation
===
Reinforcement Learning (RL) has achieved many successes over the years in training autonomous agents to perform simple tasks. However, one of the major remaining challenges in RL is scaling it to high-dimensional, real-world applications.
Although many works have already focused on strategies to scale-up RL techniques and to find solutions for more complex problems with reasonable successes, many issues still exist. This workshop encourages to discuss diverse approaches to accelerate and generalize RL, such as the use of approximations, abstractions, hierarchical approaches, and Transfer Learning.
Scaling-up RL methods has major implications on the research and practice of complex learning problems and will eventually lead to successful implementations in real-world applications.
Aims
====
This workshop intends to bridge the gap between conventional and scalable RL approaches. We aim to bring together researchers working on different approaches to scale-up RL with the goal to solve more complex or larger scale problems. We intend to make this an exciting event for researchers worldwide, not only for the presentation of top quality papers, but also to spark the discussion of opportunities and challenges for future research directions.
Topics of Interest
===
Examples of covered topics include (but are not limited to)
- Scaling Reinforcement Learning to complex problems
- Deep Reinforcement Learning
- Multiagent Reinforcement Learning
- Multiobjective Reinforcement Learning
- Transfer Learning for Reinforcement Learning
- Abstractions for Reinforcement Learning
- Approximations in Reinforcement Learning
- Relational Reinforcement Learning
- Continuous Reinforcement Learning
- Hierarchical Reinforcement Learning
- Benchmarks for Reinforcement Learning
- Large-scale applications for Reinforcement Learning
- Real-world applications for Reinforcement Learning
Paper Submission
===
The deadline for submission is July 3rd, 2017 (23:59 UTC -12:00), and decisions will be sent out on July 24th, 2017.
Authors are encouraged to submit papers to any of the following categories:
- Full Paper: Papers must be 10 - 16 pages in length. The authors are expected to present a contribution to the field.
- Short paper: Paper must be 4-6 pages in length. Papers of this category are extended abstracts of ongoing work relevant to the workshop.
- Highlight paper: Paper must be 4-6 pages in length. Papers of this category summarize full papers that have been published or accepted for publication at most 1 year before the workshop deadline (in journals or top conferences).
Submissions should be in the ECML PKDD-17 format. The review process is double-blind for full and short papers (author names and affiliations must be hidden) and single-blind for highlight papers (author identities known to reviewers). Papers will be judged according to the chosen category, significance to the workshop, proposal quality, and clarity.
Papers must be submitted through EasyChair .
PC Members
===
Reinaldo Bianchi (Centro Universitário FEI, Brazil)
Erkin Cilden (Middle East Technical University, Turkey)
Anna Helena Reali Costa (University of São Paulo, Brazil)
Sam Devlin (University of York, UK)
Katie Genter (University of Texas at Austin, USA)
Marek Grzes (University of Kent, UK)
Josiah Hanna (University of Texas at Austin, USA)
George Konidaris (Brown University, USA)
Daniel Kudenko (University of York, UK)
Matteo Leonetti (University of Leeds, UK)
Patrick MacAlpine (University of Texas at Austin, USA)
Patrick Mannion (Galway-Mayo Institute of Technology, Ireland)
Francisco Melo (Instituto Superior Técnico, Portugal)
Decebal Constantin Mocanu (Eindhoven University of Technology, Netherlands)
Sanmit Narvekar (University of Texas at Austin, USA)
Billy Okal (University of Freiburg, Germany)
Bei Peng (Washington State University, USA)
Faruk Polat (Middle East Technical University, Turkey)
Ramya Ramakrishnan (Massachusetts Institute of Technology, USA)
Matthew Taylor (Washington State University, USA)
Karl Tuyls (University of Liverpool, UK)
Peter Vamplew (Federation University Australia)
Organization
===
Workshop Chairs:
- Felipe Leno da Silva (University of São Paulo, Brazil)
- Ruben Glatt (University of São Paulo, Brazil)