SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
Zijian Guo, İlker Işık, H. M. Sabbir Ahmad, Wenchao Li
TLDR
SpecRLBench is a new benchmark to evaluate how well specification-guided reinforcement learning methods generalize across diverse tasks and environments.
Key contributions
- Introduces SpecRLBench, a benchmark for LTL-based specification-guided RL generalization.
- Spans navigation and manipulation domains with static/dynamic environments and diverse robot dynamics.
- Evaluates existing methods, highlighting their strengths, limitations, and emerging challenges.
- Provides a structured platform to compare and advance more generalizable RL methods.
Why it matters
Current specification-guided RL methods lack understanding of their generalization capabilities. This benchmark provides a critical tool to systematically assess and compare approaches across varied complexities. It will accelerate the development of more robust and generalizable RL agents.
Original Abstract
Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal logic (LTL). While recent methods have shown promising results, their ability to generalize across unseen specifications and diverse environments remains insufficiently understood. In this work, we introduce SpecRLBench, a benchmark designed to evaluate the generalization capabilities of LTL-based specification-guided RL methods. The benchmark spans multiple difficulty levels across navigation and manipulation domains, incorporating both static and dynamic environments, diverse robot dynamics, and varied observation modalities. Through extensive empirical evaluation, we characterize the strengths and limitations of existing approaches and reveal the challenges that emerge as specification and environment complexity increase. SpecRLBench provides a structured platform for systematic comparison and supports the development of more generalizable specification-guided RL methods. Code is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.