Inductive Generalization in Reinforcement Learning from Specifications

doi:10.1007/978-3-032-08707-2_13

Inductive Generalization in Reinforcement Learning from Specifications

2026-01-01

0

PRE

AI

DOI：10.1007/978-3-032-08707-2_13

Original

Original request for help

Save

Abstract

En 中文

We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These inductive tasks have similar overarching goals but they differ inductively in low-level predicates and distributions. We present a generalization procedure that leverages this inductive relationship to learn a higher-order function, a policy generator, that generates appropriately adapted policies for instances of an inductive task in a zero-shot manner. An evaluation of the proposed approach on a set of challenging control benchmarks demonstrates the promiseofourframeworkingeneralizingtounseenpoliciesforlong- horizontasks.

Keywords:

Reinforcement Learning

Inductive Generalization

Policy Generation

Logical Specifications

Zero-Shot Learning

Inductive Generalization in Reinforcement Learning from Specifications

Abstract

Journal

Organization