English
Related papers

Related papers: GALOIS: Boosting Deep Reinforcement Learning via G…

200 papers

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

Machine Learning · Computer Science 2026-02-03 Ethan Mendes , Jungsoo Park , Alan Ritter

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Mushui Liu , Weijie He , Ziqian Lu , Yunlong Yu

Program synthesis--the automated generation of executable code from high-level specifications--has been a central goal of computer science for over fifty years. This thesis provides a comparative literature review of the main paradigms that…

Programming Languages · Computer Science 2025-08-04 Zurabi Kobaladze , Anna Arnania , Tamar Sanikidze

We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-step process, which starts by mining rules from a deep RL…

Machine Learning · Computer Science 2025-03-13 Martin Tappler , Ignacio D. Lopez-Miguel , Sebastian Tschiatschek , Ezio Bartocci

Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models, where it is often difficult to incorporate expert knowledge into the models or let experts review and validate the learned…

Artificial Intelligence · Computer Science 2022-07-11 Vadim Liventsev , Aki Härmä , Milan Petković

Pre-trained Large Language Models (LLMs) are beginning to dominate the discourse around automatic code generation with natural language specifications. In contrast, the best-performing synthesizers in the domain of formal synthesis with…

Artificial Intelligence · Computer Science 2024-05-28 Yixuan Li , Julian Parsert , Elizabeth Polgreen

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical…

Artificial Intelligence · Computer Science 2019-03-01 Daoming Lyu , Fangkai Yang , Bo Liu , Steven Gustafson

Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When…

Machine Learning · Computer Science 2021-11-19 Riad Akrour , Davide Tateo , Jan Peters

Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-users, leave the synthesis problem radically ill-posed,…

Artificial Intelligence · Computer Science 2020-10-22 Yewen Pu , Kevin Ellis , Marta Kryven , Josh Tenenbaum , Armando Solar-Lezama

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

Machine Learning · Computer Science 2021-09-28 Valerie Chen , Abhinav Gupta , Kenneth Marino

Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale math-related texts for pre-training, or relies on stronger…

Computation and Language · Computer Science 2024-05-24 Kun Zhou , Beichen Zhang , Jiapeng Wang , Zhipeng Chen , Wayne Xin Zhao , Jing Sha , Zhichao Sheng , Shijin Wang , Ji-Rong Wen

Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the quality of their…

Robotics · Computer Science 2024-12-16 Charles Xu , Qiyang Li , Jianlan Luo , Sergey Levine

This paper explores continuous-time control synthesis for target-driven navigation to satisfy complex high-level tasks expressed as linear temporal logic (LTL). We propose a model-free framework using deep reinforcement learning (DRL) where…

Robotics · Computer Science 2023-03-17 Mingyu Cai , Makai Mann , Zachary Serlin , Kevin Leahy , Cristian-Ioan Vasile

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it…

Computation and Language · Computer Science 2025-10-13 Jiuheng Lin , Cong Jiang , Zirui Wu , Jiarui Sun , Yansong Feng

Program synthesis with language models (LMs) has unlocked a large set of reasoning abilities; code-tuned LMs have proven adept at generating programs that solve a wide variety of algorithmic symbolic manipulation tasks (e.g. word…

Computation and Language · Computer Science 2024-11-05 Nathaniel Weir , Muhammad Khalifa , Linlu Qiu , Orion Weller , Peter Clark

Reinforcement Learning (RL) has demonstrated promising results in learning policies for complex tasks, but it often suffers from low sample efficiency and limited transferability. Hierarchical RL (HRL) methods aim to address the difficulty…

Artificial Intelligence · Computer Science 2024-10-22 Caleb Chuck , Kevin Black , Aditya Arjun , Yuke Zhu , Scott Niekum

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers'…

Hardware Architecture · Computer Science 2024-10-11 Haocheng Xu , Haotian Hu , Sitao Huang

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches exhibit a significant challenge as they do…

Synthesizing large logic programs through symbolic Inductive Logic Programming (ILP) typically requires intermediate definitions. However, cluttering the hypothesis space with intensional predicates typically degrades performance. In…

Artificial Intelligence · Computer Science 2025-01-09 Stanisław J. Purgał , David M. Cerna , Cezary Kaliszyk

Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this process highly sample-inefficient, as models must navigate vast search spaces…

Machine Learning · Computer Science 2026-05-11 Ilia Mahrooghi , Aryo Lotfi , Emmanuel Abbe