Program Synthesis Through Reinforcement Learning Guided Tree Search

2018-06-08 · Riley Simmons-Edler, Anders Miltner, Sebastian Seung

Program Synthesis is the task of generating a program from a provided specification. Traditionally, this has been treated as a search problem by the programming languages (PL) community and more recently as a supervised learning problem by the machine learning community. Here, we propose a third approach, representing the task of synthesizing a given program as a Markov decision process solvable via reinforcement learning(RL). From observations about the states of partial programs, we attempt to find a program that is optimal over a provided reward metric on pairs of programs and states. We instantiate this approach on a subset of the RISC-V assembly language operating on floating point numbers, and as an optimization inspired by search-based techniques from the PL community, we combine RL with a priority search tree. We evaluate this instantiation and demonstrate the effectiveness of our combined method compared to a variety of baselines, including a pure RL ablation and a state of the art Markov chain Monte Carlo search method on this task.

📄 PDF Abstract BibTeX arXiv:1806.02932

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis

2023-07-13 · Julian Parsert, Elizabeth Polgreen

Program synthesis is the task of automatically generating code based on a specification. In Syntax-Guided Synthesis (SyGuS) this specification is a combination of a syntactic template and a logical formula, and the resul…

Program Synthesis reinforcement-learning Reinforcement Learning

Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis

2025-10-11 · Zhechong Huang, Zhao Zhang, Ruyi Ji, Tingxuan Xia 외 arxiv

Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by ext…

Program Synthesis Code Generation

Program Synthesis Guided Reinforcement Learning for Partially Observed Environments

2021-02-22 · NeurIPS 2021 12 · Yichen David Yang, Jeevana Priya Inala, Osbert Bastani, Yewen Pu 외

A key challenge for reinforcement learning is solving long-horizon planning problems. Recent work has leveraged programs to guide reinforcement learning in these settings. However, these approaches impose a high manual b…

Minecraft Program Synthesis reinforcement-learning Reinforcement Learning+1

Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic

2019-10-25 · Thibault Gauthier

The paper describes a deep reinforcement learning framework based on self-supervised learning within the proof assistant HOL4. A close interaction between the machine learning modules and the HOL4 library is achieved by …

Automated Theorem Proving BIG-bench Machine Learning Deep Reinforcement Learning reinforcement-learning+3

idSTLPy: A Python Toolbox for Active Perception and Control

2021-11-04 · Rafael Rodrigues da Silva, Kunal Yadav, Hai Lin

This paper describes a Python toolbox for active perception and control synthesis of probabilistic signal temporal logic (PrSTL) formulas of switched linear systems with additive Gaussian disturbances and measurement noi…

Motion Planning