Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models

12/04/2022

∙

Automata-based representations play an important role in control and planning in sequential decision-making, but obtaining high-level task knowledge for building automata is often difficult. Although large-scale generative language models (GLMs) can help automatically distill task knowledge, the textual outputs from GLMs are not directly utilizable in sequential decision-making. We resolve this problem by proposing a novel algorithm named GLM2FSA, which obtains high-level task knowledge, represented in a finite state automaton (FSA), from a given brief description of the task goal. GLM2FSA sends queries to a GLM for task knowledge in textual form and then builds a FSA to represent the textual knowledge. This algorithm fills the gap between text and automata-based representations, and the constructed FSA can be directly utilized in sequential decision-making. We provide examples to demonstrate how GLM2FSA constructs FSAs to represent knowledge encoded in the texts generated by the large-scale GLMs.

READ FULL TEXT

Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models

Multimodal Pretrained Models for Sequential Decision-Making: Synthesis, Verification, Grounding, and Perception

Learning to Generalize for Sequential Decision Making

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Knowledge-Based Sequential Decision-Making Under Uncertainty

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Approximating probabilistic models as weighted finite automata

GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks

Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models

Related Research

Multimodal Pretrained Models for Sequential Decision-Making: Synthesis, Verification, Grounding, and Perception

Learning to Generalize for Sequential Decision Making

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Knowledge-Based Sequential Decision-Making Under Uncertainty

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Approximating probabilistic models as weighted finite automata

GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks