posted by user: aedwards8 || 1638 views || tracked by 2 users: [display]

GoalsRL 2018 : 1st Workshop on Goal Specifications for Reinforcement Learning


When Jul 13, 2018 - Jul 15, 2018
Where Stockholm, Sweden
Submission Deadline May 1, 2018
Notification Due Jun 1, 2018
Final Version Due Jun 21, 2018
Categories    reinforcement learning   reward engineering   imitation learning   reward shaping

Call For Papers

We would like to invite submissions for the 1st Workshop on Goal Specifications for Reinforcement Learning at the Federated AI Meeting 2018. The submission deadline is May 1st 2018. Attached below is the call for papers. We look forward to your submissions.

ICML/IJCAI/AAMAS 2018 Workshop: Goal Specifications for Reinforcement Learning
Stockholm, Sweden

Paper submission opens: April 1st, 2018
Submission deadline: May 1st, 2018
Author notification: June 1st, 2018
Camera-ready deadline: June 21st, 2018
Workshop: July 13/14/15th, 2018

Reinforcement Learning (RL) agents traditionally rely on hand-designed scalar rewards to learn how to act. The more complex and diverse environments and tasks become, the more difficult it may be to engineer rewards that elicit desired behavior. Designing rewards in multi-agent settings with adversaries or co-operative allies can be even more complicated. Experiment designers often have a goal in mind and then must reverse engineer a reward function that will likely lead to it. This process can be difficult, especially for non-experts, and is susceptible to reward hacking---unexpected and undesired behavior that achieves high reward but does not capture the essence of what the engineer was trying to achieve. Moreover, hand-designed reward functions may be brittle, as slight changes in the environment may yield large, and potentially unsafe, alterations in agent behavior.

The community has addressed these problems through many disparate approaches including reward shaping, intrinsic rewards, hierarchical reinforcement learning, curriculum learning, and transfer learning. Another approach is to avoid designing scalar rewards altogether, and rather focus on designing goals, for example, through inverse reinforcement learning, imitation learning, target images, or multimodal channels such as speech and text.

This workshop will consider all topics related to designing goals for reinforcement learning and problems that can arise from ill-defined goals. The submissions can include novel research, open problems in the field, and surveys. We are particularly interested in the topics of reward engineering, reward hacking, interpretability, learning from humans and goal design using multimodal input.

Problems with reward design
- Robust reward functions
- Reward hacking
- Adversarial attacks on RL agents
- Generalizability of reward functions
- Communicating learned goals to humans

Methods of reward design
- Reward engineering
- Reward shaping
- Intrinsic rewards

Methods of learning rewards
- Inverse Reinforcement Learning
- Interactive learning
- Supervised learning
- Evolutionary approaches

Methods of goal design using:
- Target images
- Imitation learning
- Transfer learning
- Curriculum learning
- Hierarchical RL
- Multimodal input (speech, text, sketches, etc.)
- Multi-agent cooperative/competitive learning
- Application-related issues and solutions

Submissions will be double-blind and are limited to 4 pages for short papers and 8 pages for full papers, not including references and appendices. Formatting should be in ICML style. Concurrent submissions are allowed, but works that have been accepted at archival venues are discouraged.

Submission link:

Ashley Edwards, Georgia Institute of Technology
Himanshu Sahni, Georgia Institute of Technology
Kaushik Subramanian, Cogitai
Charles Isbell, Georgia Institute of Technology
Michael Littman, Brown University

Please address questions to:

Related Resources

ICMLA 2021   20th IEEE International Conference on Machine Learning and Applications
CFDSP 2022   2022 International Conference on Frontiers of Digital Signal Processing (CFDSP 2022)
PODS 2022   ACM Symposium on Principles of Database Systems - Call for Papers - First Submission Cycle
MLDM 2022   18th International Conference on Machine Learning and Data Mining
FAIML 2022   2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2022)
BNAIC/BENELEARN 2021   The 33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning
ICADCML 2022   3rd International Conference on Advances in Distributed Computing and Machine Learning - 2022
blockchain_ml_iot 2021   Network and Electronics (MDPI) Joint Special Issue - Blockchain and Machine Learning for IoT: Security and Privacy Challenges
XSA 2021   Explainable Deep Learning for Sentiment Analysis