The IBRL workshop will cover a wide range of topics and promote discussion on different inductive biases and their impact on different sub-fields of RL; topics include but are not limited to:
• Abstractions and structured policies: task decomposition, hierarchical RL, symmetries, etc.
• Generalization: multi-task RL, continual RL, meta RL, etc.
• Relational biases and representations: graph-based methodologies, message-passing policies, communication in MARL, composability, etc.
• Learning biases for robotics: physics priors, task-specific knowledge, geometric constraints, etc.
• Future directions: real-world applications, learning biases in RLHF, etc.
Submission Open: 01 April 2025
Submission Deadline: 30 May 2025 12 June 2025 (Anywhere on Earth)
Acceptance Notification: 15 June 2025 22 June 2025
Camera-ready submission deadline: 22 June 2025 13 July 2025
Workshop dates: 05 August 2025
Submission format: the paper must have 4-8 content pages (excluding the references and appendices).
Format: RLC 2025 author kit (please omit the cover page).
Submission portal: OpenReview.
The review process will be double-blind.
Accepted papers will be presented as posters at the workshop.
Three select papers will be given spotlight presentations (10 minutes each).
For each accepted paper, at least one co-author must register for RLC 2025 and present the work during the poster sessions.
Works that have been submitted to other venues are welcome.
Works published in other venues are also welcome if published after 1 September 2024.