A Better Variant of Self-Critical Sequence Training


In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.

Technical Report
Ruotian Luo
Ruotian Luo
Software Engineer at Waymo Perception

My research interests include computer vision, natural language processing, artificial intelligence.