Skip to main content
Proto: Program-Guided Transformer for Program-Guided Tasks
  • Zelin Zhao, The Chinese University of Hong Kong
  • Karan Samel, The Chinese University of Hong Kong
  • Binghong Chen, Georgia Tech, Georgia
  • Le Song, Biomap & Mohamed bin Zayed University of Artificial Intelligence
Document Type

Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to unify perception, reasoning, and decision making, we formulate program-guided tasks which require learning to execute a given program on the observed task specification. Furthermore, we propose Program-Guided Transformer (ProTo), which integrates both semantic and structural guidance of a program by leveraging cross-attention and masked self-attention to pass messages between the specification and routines in the program. ProTo executes a program in a learned latent space and enjoys stronger representation ability than previous neural-symbolic approaches. We demonstrate that ProTo significantly outperforms the previous state-of-the-art methods on GQA visual reasoning and 2D Minecraft policy learning datasets. Additionally, ProTo demonstrates better generalization to unseen, complex, and human-written programs. © 2021, CC BY.

Publication Date

Preprints: arXiv

Citation Information
Z. Zhao, K. Samel, B. Chen, L. Song, "ProTo: Program-guided transformer for program-guided tasks," 2021, arXiv:2110.00804