4 papers
Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
Ä°lker IÅık, Wenchao Li
Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As…
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
Zijian Guo, Ä°lker IÅık, H. M. Sabbir Ahmad +1
Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal…
One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
Zijian Guo, Ä°lker IÅık, H. M. Sabbir Ahmad +1
Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge in reinforcement learning (RL). Linear temporal logic (LTL) offe…
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
Ä°lker IÅık, Ramazan Gokberk Cinbis, Ebru Aydin Gol
Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents…