Outline, then details: Syntactically guided coarse-to-fine code generation

W Zheng, SP Sharan, AK Jaiswal… - International …, 2023 - proceedings.mlr.press
For a complicated algorithm, its implementation by a human programmer usually starts with
outlining a rough control flow followed by iterative enrichments, eventually yielding carefully …

Hierarchical programmatic reinforcement learning via learning to compose programs

GT Liu, EP Hu, PJ Cheng, HY Lee… - … on Machine Learning, 2023 - proceedings.mlr.press
Aiming to produce reinforcement learning (RL) policies that are human-interpretable and
can generalize better to novel scenarios, Trivedi et al.(2021) present a method (LEAPS) that …

Addressing long-horizon tasks by integrating program synthesis and state machines

YA Lin, CT Lee, GT Liu, PJ Cheng, SH Sun - arXiv preprint arXiv …, 2023 - arxiv.org
Deep reinforcement learning excels in various domains but lacks generalizability and
interoperability. Programmatic RL methods (Trivedi et al., 2021; Liu et al., 2023) reformulate …

AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning

J Zenkner, L Dierkes, T Sesterhenn… - arXiv preprint arXiv …, 2024 - arxiv.org
LambdaBeam is a state-of-the-art execution-guided algorithm for program synthesis that
incorporates higher-order functions, lambda functions, and iterative loops into the Domain …