English
Related papers

Related papers: Program Synthesis Through Reinforcement Learning G…

200 papers

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

Most work on query optimization has concentrated on loop-free queries. However, data science and machine learning workloads today typically involve recursive or iterative computation. In this work, we propose a novel framework for…

Databases · Computer Science 2022-02-22 Yisu Remy Wang , Mahmoud Abo Khamis , Hung Q. Ngo , Reinhard Pichler , Dan Suciu

The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small…

Logic in Computer Science · Computer Science 2023-05-31 Rajeev Alur , Osbert Bastani , Kishor Jothimurugan , Mateo Perez , Fabio Somenzi , Ashutosh Trivedi

Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…

Machine Learning · Computer Science 2017-06-29 Rudy Bunel , Alban Desmaison , M. Pawan Kumar , Philip H. S. Torr , Pushmeet Kohli

Non-stationary domains, where unforeseen changes happen, present a challenge for agents to find an optimal policy for a sequential decision making problem. This work investigates a solution to this problem that combines Markov Decision…

Artificial Intelligence · Computer Science 2017-05-04 Leonardo A. Ferreira , Reinaldo A. C. Bianchi , Paulo E. Santos , Ramon Lopez de Mantaras

We present a novel approach to the automatic synthesis of recursive programs from mixed-quantifier first-order logic properties. Our approach uses Skolemization to reduce the mixed-quantifier synthesis problem to a $\forall^*$-synthesis…

Logic in Computer Science · Computer Science 2026-01-08 Derek Egolf , Stavros Tripakis

We present a method for the synthesis of polynomial lasso programs. These programs consist of a program stem, a set of transitions, and an exit condition, all in the form of algebraic assertions (conjunctions of polynomial equalities).…

Logic in Computer Science · Computer Science 2013-11-19 Jan Leike , Ashish Tiwari

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are hard to leverage in real-world systems due…

Machine Learning · Computer Science 2021-03-05 Gabriel Dulac-Arnold , Nir Levine , Daniel J. Mankowitz , Jerry Li , Cosmin Paduraru , Sven Gowal , Todd Hester

Reformulating the history matching problem from a least-square mathematical optimization problem into a Markov Decision Process introduces a method in which reinforcement learning can be utilized to solve the problem. This method provides a…

Machine Learning · Computer Science 2022-12-26 Omar S. Alolayan , Abdullah O. Alomar , John R. Williams

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during…

Computation and Language · Computer Science 2025-08-07 Bowen Jin , Hansi Zeng , Zhenrui Yue , Jinsung Yoon , Sercan Arik , Dong Wang , Hamed Zamani , Jiawei Han

Program synthesis aims to automatically generate an executable program that conforms to the given specification. Recent advancements have demonstrated that deep neural methodologies and large-scale pretrained language models are highly…

Robotics · Computer Science 2023-12-14 Tianyi Chen , Qidi Wang , Zhen Dong , Liwei Shen , Xin Peng

Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks…

Artificial Intelligence · Computer Science 2025-03-19 Huatong Song , Jinhao Jiang , Yingqian Min , Jie Chen , Zhipeng Chen , Wayne Xin Zhao , Lei Fang , Ji-Rong Wen

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of…

Machine Learning · Computer Science 2019-08-19 Daniel S. Brown , Scott Niekum

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yuanzhi Liang , Yijie Fang , Ke Hao , Rui Li , Ziqi Ni , Ruijie Su , Chi Zhang

Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on…

Artificial Intelligence · Computer Science 2025-12-18 Toshihide Ubukata , Enhong Mu , Takuto Yamauchi , Mingyue Zhang , Jialong Li , Kenji Tei

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1,…

Machine Learning · Computer Science 2025-06-13 Wei Xiong , Jiarui Yao , Yuhui Xu , Bo Pang , Lei Wang , Doyen Sahoo , Junnan Li , Nan Jiang , Tong Zhang , Caiming Xiong , Hanze Dong

Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional…

Machine Learning · Computer Science 2025-10-02 Carlo Bosio , Matteo Guarrera , Alberto Sangiovanni-Vincentelli , Mark W. Mueller

Generalised planning (GP) refers to the task of synthesising programs that solve families of related planning problems. We introduce a novel, yet simple method for GP: given a set of training problems, for each problem, compute an optimal…

Artificial Intelligence · Computer Science 2025-11-17 Dillon Z. Chen , Till Hofmann , Toryn Q. Klassen , Sheila A. McIlraith

Superoptimization requires the estimation of the best program for a given computational task. In order to deal with large programs, superoptimization techniques perform a stochastic search. This involves proposing a modification of the…

Machine Learning · Computer Science 2016-12-06 Rudy Bunel , Alban Desmaison , M. Pawan Kumar , Philip H. S. Torr , Pushmeet Kohli