English
Related papers

Related papers: Controlled Decoding from Language Models

200 papers

While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels leads to the scaling up dilemma, especially for complex tasks.…

Machine Learning · Computer Science 2026-03-17 Zizhuo Zhang , Jianing Zhu , Xinmu Ge , Zihua Zhao , Zhanke Zhou , Xuan Li , Xiao Feng , Jiangchao Yao , Bo Han

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

Machine Learning · Computer Science 2026-05-21 Haitong Ma , Ofir Nabati , Aviv Rosenberg , Bo Dai , Oran Lang , Craig Boutilier , Na Li , Shie Mannor , Lior Shani , Guy Tenneholtz

Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. The RL framework has become promising due…

Systems and Control · Electrical Eng. & Systems 2024-07-29 Pouria Razzaghi , Amin Tabrizian , Wei Guo , Shulu Chen , Abenezer Taye , Ellis Thompson , Alexis Bregeon , Ali Baheri , Peng Wei

Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pretraining (CLIP),…

Machine Learning · Computer Science 2022-11-10 Tarun Gupta , Peter Karkus , Tong Che , Danfei Xu , Marco Pavone

Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…

Computation and Language · Computer Science 2025-06-10 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Yancheng Yuan , Dacheng Tao

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative…

Computation and Language · Computer Science 2024-03-14 Hongyi Yuan , Keming Lu , Fei Huang , Zheng Yuan , Chang Zhou

Multi-Task Learning (MTL) in Neural Combinatorial Optimization (NCO) is a promising approach to train a unified model capable of solving multiple Vehicle Routing Problem (VRP) variants. However, existing Reinforcement Learning (RL)-based…

Machine Learning · Computer Science 2025-11-05 Yuepeng Zheng , Fu Luo , Zhenkun Wang , Yaoxin Wu , Yu Zhou

Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such as offensiveness, social bias, harmfulness or falsehood.…

Machine Learning · Computer Science 2022-10-24 Tomasz Korbak , Ethan Perez , Christopher L Buckley

We introduce a large language model (LLM) capable of processing speech inputs and show that tuning it further with reinforcement learning on human preference (RLHF) enables it to adapt better to disordered speech than traditional…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Chirag Nagpal , Subhashini Venugopalan , Jimmy Tobin , Marilyn Ladewig , Katherine Heller , Katrin Tomanek

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…

Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in…

Computation and Language · Computer Science 2024-03-20 Zishun Yu , Yunzhe Tao , Liyu Chen , Tao Sun , Hongxia Yang

Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging and labor-intensive process due to the inefficiencies and inconsistencies inherent in traditional methods. Existing methods…

Machine Learning · Computer Science 2026-04-16 Shentong Mo

Reinforcement Learning (RL) is a computational approach to reward-driven learning in sequential decision problems. It implements the discovery of optimal actions by learning from an agent interacting with an environment rather than from…

Methodology · Statistics 2022-10-06 Mauricio Tec , Yunshan Duan , Peter Müller

What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both…

Multiagent Systems · Computer Science 2020-01-03 Ismael T. Freire , Clement Moulin-Frier , Marti Sanchez-Fibla , Xerxes D. Arsiwalla , Paul Verschure

This paper delves into designing stabilizing feedback control gains for continuous linear systems with unknown state matrix, in which the control is subject to a general structural constraint. We bring forth the ideas from reinforcement…

Systems and Control · Electrical Eng. & Systems 2025-11-11 Sayak Mukherjee , Thanh Long Vu

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task…

Machine Learning · Computer Science 2025-10-28 Haozhe Ma , Zhengding Luo , Thanh Vinh Vo , Kuankuan Sima , Tze-Yun Leong

We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation.…

Artificial Intelligence · Computer Science 2026-04-17 Ana María Gómez Ruiz , Thao Dang , Alexandre Donzé

Complex systems are ubiquitous in the real world and tend to have complicated and poorly understood dynamics. For their control issues, the challenge is to guarantee accuracy, robustness, and generalization in such bloated and troubled…

Artificial Intelligence · Computer Science 2022-09-16 Xuehui Yu , Jingchi Jiang , Xinmiao Yu , Yi Guan , Xue Li

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia
‹ Prev 1 8 9 10 Next ›