How to Solve Contextual Goal-Oriented Problems with Offline Datasets?

TL;DR

This paper introduces CODA, a new method leveraging unlabeled trajectories and context-goal pairs to solve complex goal-oriented problems offline, with theoretical guarantees and superior empirical performance.

Contribution

The paper proposes CODA, a novel data augmentation technique that constructs an action-augmented MDP to solve CGO problems without additional approximation errors.

Findings

CODA outperforms baseline methods across various CGO scenarios.

Theoretical analysis confirms CODA's capability to solve CGO problems offline.

Empirical results demonstrate CODA's effectiveness in diverse contexts.

Abstract

We present a novel method, Contextual goal-Oriented Data Augmentation (CODA), which uses commonly available unlabeled trajectories and context-goal pairs to solve Contextual Goal-Oriented (CGO) problems. By carefully constructing an action-augmented MDP that is equivalent to the original MDP, CODA creates a fully labeled transition dataset under training contexts without additional approximation error. We conduct a novel theoretical analysis to demonstrate CODA's capability to solve CGO problems in the offline data setup. Empirical results also showcase the effectiveness of CODA, which outperforms other baseline methods across various context-goal relationships of CGO problem. This approach offers a promising direction to solving CGO problems using offline datasets.