Papers › SAINT: Attention-Based Modeling of Sub-Action Dependencies in Multi-Action Policies

SAINT: Attention-Based Modeling of Sub-Action Dependencies in Multi-Action Policies

17 May 2025arXiv:2505.12109archive 2025-07-28

Matthew Landers, Taylor W. Killian, Thomas Hartvigsen, Afsaneh Doryab

The combinatorial structure of many real-world action spaces leads to exponential growth in the number of possible actions, limiting the effectiveness of conventional reinforcement learning algorithms. Recent approaches for combinatorial action spaces impose factorized or sequential structures over sub-actions, failing to capture complex joint behavior. We introduce the Sub-Action Interaction Network using Transformers (SAINT), a novel policy architecture that represents multi-component actions as unordered sets and models their dependencies via self-attention conditioned on the global state. SAINT is permutation-invariant, sample-efficient, and compatible with standard policy optimization algorithms. In 15 distinct combinatorial environments across three task domains, including environments with nearly 17 million joint actions, SAINT consistently outperforms strong baselines.

PaperPDFCode

Code

matthewlanders/saint officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CutMixDense ConnectionsFeedforward NetworkMixupSAINT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections