English
Related papers

Related papers: Objective-Specific Privileged Bases via Full-Prefi…

200 papers

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically…

Computation and Language · Computer Science 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Computation and Language · Computer Science 2025-10-21 Mingye Zhu , Yi Liu , Zheren Fu , Yongdong Zhang , Zhendong Mao

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. The goal of the…

Machine Learning · Computer Science 2022-05-25 Xiaoyu Chen , Han Zhong , Zhuoran Yang , Zhaoran Wang , Liwei Wang

Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on…

Machine Learning · Computer Science 2024-01-31 Zhuo Wang , Wei Zhang , Ning Liu , Jianyong Wang

In recent years, deep discrete representation learning (DRL) has achieved significant success across various domains. Most DRL frameworks (e.g., the widely used VQ-VAE and its variants) have primarily focused on generative settings, where…

Machine Learning · Computer Science 2025-06-16 Tung-Long Vuong

Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgoals. The main challenge of HRL is efficient discovery of the…

Machine Learning · Computer Science 2025-07-08 Sadegh Khorasani , Saber Salehkaleybar , Negar Kiyavash , Matthias Grossglauser

The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Zifu Wang , Junyi Zhu , Bo Tang , Zhiyu Li , Feiyu Xiong , Jiaqian Yu , Matthew B. Blaschko

Hierarchical Reinforcement Learning (HRL) is a promising approach to solving long-horizon problems with sparse and delayed rewards. Many existing HRL algorithms either use pre-trained low-level skills that are unadaptable, or require…

Machine Learning · Computer Science 2019-10-11 Siyuan Li , Rui Wang , Minxue Tang , Chongjie Zhang

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in…

Artificial Intelligence · Computer Science 2019-10-08 Xi Chen , Ali Ghadirzadeh , Mårten Björkman , Patric Jensfelt

While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have…

Artificial Intelligence · Computer Science 2023-06-02 Yan Zeng , Ruichu Cai , Fuchun Sun , Libo Huang , Zhifeng Hao

The main focus of Hierarchical Reinforcement Learning (HRL) is studying how large Markov Decision Processes (MDPs) can be more efficiently solved when addressed in a modular way, by combining partial solutions computed for smaller subtasks.…

Machine Learning · Computer Science 2025-12-05 Roberto Cipollone , Luca Iocchi , Matteo Leonetti

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Artificial Intelligence · Computer Science 2025-03-19 Anukriti Singh , Amisha Bhaskar , Peihong Yu , Souradip Chakraborty , Ruthwik Dasyam , Amrit Bedi , Pratap Tokekar

This paper examines the characterization and learning of grammars defined with enriched representational models. Model-theoretic approaches to formal language theory traditionally assume that each position in a string belongs to exactly one…

Formal Languages and Automata Theory · Computer Science 2019-06-25 Jane Chandlee , Remi Eyraud , Jeffrey Heinz , Adam Jardine , Jonathan Rawski

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Tianjun Zhang , Ruslan Salakhutdinov , Sergey Levine

Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximization or variational…

Machine Learning · Computer Science 2023-10-31 Seongun Kim , Kyowoon Lee , Jaesik Choi

Classical theory in reinforcement learning (RL) predominantly focuses on the single task setting, where an agent learns to solve a task through trial-and-error experience, given access to data only from that task. However, many recent…

Machine Learning · Computer Science 2022-06-28 Aldo Pacchiano , Ofir Nachum , Nilseh Tripuraneni , Peter Bartlett

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on…

Robotics · Computer Science 2025-12-02 Ruiqi Wang , Dezhong Zhao , Ziqin Yuan , Tianyu Shao , Guohua Chen , Dominic Kao , Sungeun Hong , Byung-Cheol Min

Although the foundations of ranking are well established, the ranking literature has primarily been focused on simple, unimodal models, e.g. the Mallows and Plackett-Luce models, that define distributions centered around a single total…

Machine Learning · Computer Science 2023-12-27 Arjun Seshadri , Stephen Ragain , Johan Ugander

We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy…

Computation and Language · Computer Science 2023-10-17 Weiwen Xu , Xin Li , Wenxuan Zhang , Meng Zhou , Wai Lam , Luo Si , Lidong Bing

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiable Rewards (RLVR)…

Machine Learning · Computer Science 2025-10-24 Dian Yu , Yulai Zhao , Kishan Panaganti , Linfeng Song , Haitao Mi , Dong Yu