English
Related papers

Related papers: The Trajectory Alignment Coefficient in Two Acts: …

200 papers

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

Machine Learning · Computer Science 2025-12-09 Ruiyi Wang , Prithviraj Ammanabrolu

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Computation and Language · Computer Science 2024-09-19 Hang Zhou , Chenglong Wang , Yimin Hu , Tong Xiao , Chunliang Zhang , Jingbo Zhu

Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore…

Computation and Language · Computer Science 2024-02-28 Nuo Xu , Jun Zhao , Can Zu , Sixian Li , Lu Chen , Zhihao Zhang , Rui Zheng , Shihan Dou , Wenjuan Qin , Tao Gui , Qi Zhang , Xuanjing Huang

Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains…

Machine Learning · Computer Science 2023-06-28 Weichen Li , Rati Devidze , Sophie Fellenz

To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An…

Robotics · Computer Science 2019-07-16 Xingyu Lin , Harjatin Singh Baweja , David Held

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

Artificial Intelligence · Computer Science 2021-07-23 Xuan Zhao , Marcos Campos

Dynamic Algorithm Configuration (DAC) has garnered significant attention in recent years, particularly in the prevalence of machine learning and deep learning algorithms. Numerous studies have leveraged the robustness of decision-making in…

Machine Learning · Computer Science 2025-07-10 Tai Nguyen , Phong Le , André Biedenkapp , Carola Doerr , Nguyen Dang

Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem,…

Networking and Internet Architecture · Computer Science 2023-03-30 Abhisek Konar , Di Wu , Yi Tian Xu , Seowoo Jang , Steve Liu , Gregory Dudek

The burgeoning field of autonomous driving necessitates the seamless integration of autonomous vehicles (AVs) with human-driven vehicles, calling for more predictable AV behavior and enhanced interaction with human drivers. Human-like…

Computational Engineering, Finance, and Science · Computer Science 2024-08-09 Yuting Wang , Lu Liu , Maonan Wang , Xi Xiong

Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a reward function takes considerable hand…

Computer Vision and Pattern Recognition · Computer Science 2017-06-14 Pierre Sermanet , Kelvin Xu , Sergey Levine

Reinforcement learning (RL) has enhanced the capabilities of large language models (LLMs) through reward-driven training. Nevertheless, this process can introduce excessively long responses, inflating inference latency and computational…

Machine Learning · Computer Science 2026-02-17 Chang Liu , Yiran Zhao , Lawrence Liu , Yaoqi Ye , Csaba Szepesvári , Lin F. Yang

Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely…

Machine Learning · Computer Science 2025-06-02 Yongming Chen , Miner Chen , Liewen Liao , Mingyang Jiang , Xiang Zuo , Hengrui Zhang , Yuchen Xi , Songan Zhang

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…

Machine Learning · Computer Science 2022-01-04 Markus Peschl , Arkady Zgonnikov , Frans A. Oliehoek , Luciano C. Siebert

Reinforcement learning from human feedback (RLHF) has been crucial in aligning large language models (LLMs) with human values. Traditionally, RLHF involves generating responses to a query and using a reward model to assign a reward to the…

Computation and Language · Computer Science 2024-12-04 Wenxuan Zhou , Shujian Zhang , Lingxiao Zhao , Tao Meng

Behavior and motion planning play an important role in automated driving. Traditionally, behavior planners instruct local motion planners with predefined behaviors. Due to the high scene complexity in urban environments, unpredictable…

Robotics · Computer Science 2020-09-15 Sascha Rosbach , Vinit James , Simon Großjohann , Silviu Homoceanu , Stefan Roth

Reinforcement learning (RL) has enabled major advances in fields such as robotics and natural language processing. A key challenge in RL is measuring task complexity, which is essential for creating meaningful benchmarks and designing…

Machine Learning · Computer Science 2026-02-24 Reabetswe M. Nkhumise , Mohamed S. Talamali , Aditya Gilra

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

Machine Learning · Computer Science 2026-01-26 Chengyang Ying , Xinning Zhou , Zhongkai Hao , Hang Su , Songming Liu , Dong Yan , Jun Zhu

Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy…

Machine Learning · Computer Science 2024-04-03 Kyuyoung Kim , Jongheon Jeong , Minyong An , Mohammad Ghavamzadeh , Krishnamurthy Dvijotham , Jinwoo Shin , Kimin Lee

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Machine Learning · Computer Science 2025-09-30 Xingwu Chen , Tianle Li , Difan Zou