[Amdnl] CfP: Workshop on Human Aligned Reinforcement Learning for Autonomous Agents and Robots

[Francisco Cruz]

Call for Papers: ICDL 2021 Workshop:
*Human Aligned Reinforcement Learning for Autonomous Agents and Robots*
Website: https://harlworkshop.github.io/
Date: August 27th, 2021 Virtual (submission deadline: July 02, 2021)
=============================

We invite researchers from the reinforcement learning and robotics
community to submit their recent works pertaining to the issue of
incorporating human-related aspects into (deep) reinforcement learning
agents and robots.

The focus of this workshop is to bring together researchers from the fields
of robotics and reinforcement learning to discuss and share
state-of-the-art methods, challenges and novel solutions pertaining to the
issue of incorporating human-related aspects into reinforcement learning
agents and robots. We hope to provide an opportunity to discuss
fundamental, current issues and future research directions to foster the
presence of autonomous agents and robots in real-world scenarios. The main
topics of interest are explainability, interactivity, safety, and ethics in
social robotics and autonomous agents, especially from a reinforcement
learning perspective. In this regard, approaches with special interest for
this workshop are (but not limited to):

- Explainability, interpretability, and transparency methods for
feature-oriented and goal-driven RL
- Explainable robotic systems with RL approaches
- Assisted and interactive RL in human-robot and human-agent scenarios
- Human-in-the-loop RL and applications
- RL from demonstrations and imperfect demonstrations
- Robot and agent learning from multiple human sources
- Multi-robot systems with human collaboration
- Safe exploration during learning
- Ethical reasoning and moral uncertainty
- Fairness in RL and multi-agent systems
- Theory of mind based RL frameworks
- Use of human priors in RL

Submissions must be in PDF, formatted using the IEEE conference style in
two columns. We invite submissions of both:

- Extended abstracts (up to 2 pages including references)
- Full papers (up to 6 pages including references)

Selected contributions will be presented during the workshop as spotlight
talks and in a poster session. Accepted papers will be uploaded to the
workshop website, but are free to appear in other journals or conference
proceedings.

Contributors to the workshop will be invited to submit extended versions of
the manuscripts to a topical collection (special issue) at Neural Computing
and Applications (https://www.springer.com/journal/521/updates/19055662).


*Key Dates:*
Submission Deadline: July 2, 2021 (11:59 pm AOE)
Acceptance Notification: July 30, 2021
Camera-ready version: August 12, 2021 (11:59 pm AOE)
Workshop: August 27, 2021


*Invited Speakers:*
Matthew Taylor, University of Alberta, Canada.
Alessandra Sciutti, IIT, Italy.
Stefan Wermter, University of Hamburg, Germany.
Peter Vamplew, Federation University, Australia.
Bradley Knox, Bosch, USA.
Benjamin Rosman, University of the Witwatersrand, South Africa.
Felipe Leno da Silva, São Paulo State University UNESP, Brazil.
Jens Kober, Delft University of Technology, The Netherlands.
Bruno Fernandes, University of Pernambuco, Brazil.
Nicolas Navarro-Guerrero, Aarhus University, Denmark.
George Konidaris, Brown University, USA.
Richard Dazeley, Deakin University, Australia.


*Organizers:*
Francisco Cruz (School of Information Technology, Deakin University,
Australia)
Thommen George Karimpanal (Applied Artificial Intelligence Institute,
Deakin University, Australia)
Miguel Solis (Facultad de Ingeniería, Universidad Andrés Bello, Chile)
Pablo Barros (Cognitive Architecture for Collaborative Technologies Unit,
Istituto Italiano di Tecnologia, Italy)
Richard Dazeley (Machine Intelligence Lab, Deakin University, Australia)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cse.msu.edu/pipermail/amdnl/attachments/20210531/69a5af74/attachment-0001.html>