Sequence Generation with Guider Network

TL;DR

This paper introduces a guider network for sequence generation that provides intermediate rewards, addressing the sparse-reward problem in reinforcement learning and improving sequence quality.

Contribution

The paper proposes a novel guider network that models the sequence-generation environment and supplies intermediate rewards, enhancing RL-based sequence generation.

Findings

Improved sequence quality in unconditional tasks

Enhanced performance in conditional sequence generation

Effective handling of sparse-reward problem

Abstract

Sequence generation with reinforcement learning (RL) has received significant attention recently. However, a challenge with such methods is the sparse-reward problem in the RL training process, in which a scalar guiding signal is often only available after an entire sequence has been generated. This type of sparse reward tends to ignore the global structural information of a sequence, causing generation of sequences that are semantically inconsistent. In this paper, we present a model-based RL approach to overcome this issue. Specifically, we propose a novel guider network to model the sequence-generation environment, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments show that the proposed method leads to improved performance for both unconditional and conditional sequence-generation tasks.