LTL-Transfer: Skill Transfer for Temporal Task Specification
Jason Xinyu Liu, Ankit Shah, Eric Rosen, Mingxi Jia, George Konidaris,, Stefanie Tellex

TL;DR
LTL-Transfer enables robots to generalize to new tasks specified by linear temporal logic without additional training, by composing learned skills to ensure safety and efficiency in diverse environments.
Contribution
The paper introduces LTL-Transfer, a zero-shot transfer algorithm that composes task-agnostic skills for novel LTL task specifications, reducing training data requirements.
Findings
Achieves over 90% success on unseen tasks after training on 50 tasks.
Solves 100% of 300 novel tasks without safety violations.
Demonstrated effective transfer on a quadruped robot for fetch-and-deliver and navigation tasks.
Abstract
Deploying robots in real-world environments, such as households and manufacturing lines, requires generalization across novel task specifications without violating safety constraints. Linear temporal logic (LTL) is a widely used task specification language with a compositional grammar that naturally induces commonalities among tasks while preserving safety guarantees. However, most prior work on reinforcement learning with LTL specifications treats every new task independently, thus requiring large amounts of training data to generalize. We propose LTL-Transfer, a zero-shot transfer algorithm that composes task-agnostic skills learned during training to safely satisfy a wide variety of novel LTL task specifications. Experiments in Minecraft-inspired domains show that after training on only 50 tasks, LTL-Transfer can solve over 90% of 100 challenging unseen tasks and 100% of 300 commonly…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Robot Manipulation and Learning · Software Testing and Debugging Techniques
