English
Related papers

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

200 papers

In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning…

Computer Science and Game Theory · Computer Science 2024-11-08 Luise Ge , Daniel Halpern , Evi Micha , Ariel D. Procaccia , Itai Shapira , Yevgeniy Vorobeychik , Junlin Wu

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Computation and Language · Computer Science 2021-04-13 Zhengxu Hou , Bang Liu , Ruihui Zhao , Zijing Ou , Yafei Liu , Xi Chen , Yefeng Zheng

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…

Machine Learning · Computer Science 2021-06-07 Johan Bjorck , Xiangyu Chen , Christopher De Sa , Carla P. Gomes , Kilian Q. Weinberger

Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these…

Machine Learning · Computer Science 2024-02-21 Idan Shenfeld , Zhang-Wei Hong , Aviv Tamar , Pulkit Agrawal

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Autonomous racing is becoming popular for academic and industry researchers as a test for general autonomous driving by pushing perception, planning, and control algorithms to their limits. While traditional control methods such as MPC are…

Robotics · Computer Science 2023-07-07 Edoardo Ghignone , Nicolas Baumann , Mike Boss , Michele Magno

Predicting public transit incident duration from unstructured text alerts is a critical but challenging task. Addressing the domain sparsity of transit operations with standard Supervised Fine-Tuning (SFT) is difficult, as the task involves…

Artificial Intelligence · Computer Science 2025-11-04 Bowen Fang , Ruijian Zha , Xuan Di

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Machine Learning · Computer Science 2024-02-13 Siyuan Li , Shijie Han , Yingnan Zhao , By Liang , Peng Liu

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

Computation and Language · Computer Science 2025-12-02 Vijay Viswanathan , Yanchao Sun , Shuang Ma , Xiang Kong , Meng Cao , Graham Neubig , Tongshuang Wu

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of significant steady-state errors often manifest when quadratic reward functions are…

Systems and Control · Electrical Eng. & Systems 2024-04-02 Liyao Wang , Zishun Zheng , Yuan Lin

The black-box nature of deep reinforcement learning (RL) hinders them from real-world applications. Therefore, interpreting and explaining RL agents have been active research topics in recent years. Existing methods for post-hoc…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Huanqian Wang , Mukun Tong , Wenjie Shi , Gao Huang , Shiji Song

We propose a novel composite reward function for reinforcement learning in financial trading that balances return and risk using four differentiable terms: annualized return downside risk differential return and the Treynor ratio Unlike…

Machine Learning · Computer Science 2025-06-06 Uditansh Srivastava , Shivam Aryan , Shaurya Singh

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Samuel Barbeau , Pedram Fekri , David Osowiechi , Ali Bahri , Moslem Yazdanpanah , Masih Aminbeidokhti , Christian Desrosiers

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation…

Machine Learning · Computer Science 2025-10-06 Anisha Gunjal , Anthony Wang , Elaine Lau , Vaskar Nath , Yunzhong He , Bing Liu , Sean Hendryx

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

Computation and Language · Computer Science 2024-04-09 Bowen Qin , Duanyu Feng , Xi Yang

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

Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works cannot learn incrementally from an ongoing trajectory…

Machine Learning · Computer Science 2025-07-24 Shicheng Liu , Minghui Zhu

With the increasing availability of traffic data and advance of deep reinforcement learning techniques, there is an emerging trend of employing reinforcement learning (RL) for traffic signal control. A key question for applying RL to…

Machine Learning · Computer Science 2019-05-14 Guanjie Zheng , Xinshi Zang , Nan Xu , Hua Wei , Zhengyao Yu , Vikash Gayah , Kai Xu , Zhenhui Li