Environment-Independent Task Specifications via GLTL

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.

References in corpus (1)

• Decision-Theoretic Planning: Structural Assumptions and Computational Leverage

Cited by in corpus (21)

• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
• Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions
• Learning to Compose Skills
• LTL2Action: Generalizing LTL Instructions for Multi-Task RL
• Planning With Uncertain Specifications (PUnS)
• Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning
• Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning
• Design Space of Behaviour Planning for Autonomous Driving
• Goals as Reward-Producing Programs
• Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications
• Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs
• Interactive Robot Training for Non-Markov Tasks
• Formal Language Constraints for Markov Decision Processes
• Constraint Satisfaction Propagation: Non-stationary Policy Synthesis for Temporal Logic Planning
• A First-Occupancy Representation for Reinforcement Learning
• Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning
• MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning
• Embedding Symbolic Temporal Knowledge into Deep Sequential Models
• Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator
• Generalized Inverse Planning: Learning Lifted non-Markovian Utility for Generalizable Task Representation