Call for Submissions: 2nd Workshop on Learning Effective Abstractions for Planning at CoRL 2024

Greetings! We are excited to announce the call for submissions to the 2nd Workshop on Learning Effective Abstractions for Planning (LEAP) to be held at CoRL 2024 in Munich, Germany. The workshop aims to bring together researchers from various sub-communities such as task and motion planning, reinforcement learning, planning with formal logic, planning with natural language, and neuro-symbolic AI to share insights and discuss key questions related to learning symbolic representations that support planning.

The key questions for discussion include the right objective for abstraction learning, the level of abstraction needed for effectiveness, interpretability and explainability of abstractions, the use of pre-trained foundational models, and the timing and data sources for abstraction learning.

We invite submissions on areas of interest such as learning generalizable and composable representations, learning for task and motion planning, learning state and action abstractions, natural language as an abstraction, and learning for hierarchical planning, among others. The deadline for paper submissions is September 22, 2024.

For more information, please visit the workshop website or email leap-workshop at googlegroups.com.