Environment-Independent Task Specifications via GLTL

2017/04/14 by Littman, Michael L., Topcu, Ufuk, Fu, Jie +3 · 2 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1704.04341

Abstract

We propose a new task-specification language for Markov decision processes that is designed to be an improvement over reward functions by being environment independent. The language is a variant of Linear Temporal Logic (LTL) that is extended to probabilistic specifications in a way that permits approximations to be learned in finite time. We provide several small environments that demonstrate the advantages of our geometric LTL (GLTL) language and illustrate how it can be used to specify standard reinforcement-learning tasks straightforwardly.

Cited by

• RLAF: Reinforcement Learning from Automaton Feedback
• Fully Learnable Neural Reward Machines

Related

• Generalizing LTL Instructions via Future Dependent Options
• On the (In)Tractability of Reinforcement Learning for LTL Objectives
• Unifying task specification in reinforcement learning
• Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration
• Modular Deep Reinforcement Learning with Temporal Logic Specifications