CEDAR: A Counter-Example Driven Agent with Regular Restriction

Lekai Chen, Alvaro Velasquez, Ashutosh Trivedi

Keywords: Automata Learning, AI Alignment

Abstract:

We introduce CEDAR, a Counter-Example Driven Agent with Regular Restrictions in Minecraft, which learns and encodes informal specifications and skills as regular languages.
Our formalizer constructs deterministic finite automata (DFAs) to represent informal specifications by utilizing membership query responses from a Large Language Model (LLM) and counterexamples provided by a human.
The DFA alphabet is derived from a global set of environmental events, with words in the language representing expected event sequences.
These learned DFAs are then used by CEDAR's skill learner to acquire the necessary skills to fulfill the specifications.
CEDAR supports both goal completion and lifelong learning by leveraging passive and active DFA learning algorithms, respectively.
The DFAs for skills are refined through counterexamples generated from DFA simulations in the real environment.
Skills acquired by CEDAR can be adapted to new scenarios by modifying the alphabet and can be logically verified to ensure they meet expected properties.
Empirical evaluations demonstrate that CEDAR surpasses state-of-the-art methods in controllability, robustness, and extensibility.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 24302