Author

Kaisheng Zhao

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Mask-based Predictive Representations for Reinforcement Learning

This work proposes a self-supervised task based on mask prediction as an auxiliary task for reinforcement learning that outperforms state-of-the-art sample-efficient reinforcement learning methods on multiple continuous and discrete control benchmarks.

Kaisheng Zhao · 0 citations