English
Related papers

Related papers: Uncertainty-Aware Reward Discounting for Mitigatin…

200 papers

Aligning multimodal large language models (MLLMs) with human preferences often relies on single-signal, model-based reward methods. Such monolithic rewards often lack confidence calibration across domain-specific tasks, fail to capture…

Artificial Intelligence · Computer Science 2025-10-08 Radha Gulhane , Sathish Reddy Indurthi

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Machine Learning · Computer Science 2024-07-04 Adam X. Yang , Maxime Robeyns , Thomas Coste , Zhengyan Shi , Jun Wang , Haitham Bou-Ammar , Laurence Aitchison

Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…

Artificial Intelligence · Computer Science 2026-03-06 Minjune Hwang , Yigit Korkmaz , Daniel Seita , Erdem Bıyık

This paper addresses the challenge of model uncertainty in quantitative finance, where decisions in portfolio allocation, derivative pricing, and risk management rely on estimating stochastic models from limited data. In practice, the…

Computational Finance · Quantitative Finance 2025-06-10 Hans Buehler , Blanka Horvath , Yannick Limmer , Thorsten Schmidt

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

Machine Learning · Computer Science 2022-01-10 Weichao Zhou , Wenchao Li

This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize…

Machine Learning · Computer Science 2023-05-18 Gen Li , Wenhao Zhan , Jason D. Lee , Yuejie Chi , Yuxin Chen

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Machine Learning · Statistics 2025-01-03 Pangpang Liu , Chengchun Shi , Will Wei Sun

Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty. For example, the reward can be the negative entropy of the agent's…

Artificial Intelligence · Computer Science 2020-05-12 Yash Satsangi , Sungsu Lim , Shimon Whiteson , Frans Oliehoek , Martha White

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting…

Artificial Intelligence · Computer Science 2021-12-20 Jasmina Gajcin , Rahul Nair , Tejaswini Pedapati , Radu Marinescu , Elizabeth Daly , Ivana Dusparic

Given two sources of evidence about a latent variable, one can combine the information from both by multiplying the likelihoods of each piece of evidence. However, when one or both of the observation models are misspecified, the…

Machine Learning · Computer Science 2021-03-24 Dmitrii Krasheninnikov , Rohin Shah , Herke van Hoof

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications…

Machine Learning · Computer Science 2026-05-18 Mehul Damani , Isha Puri , Stewart Slocum , Idan Shenfeld , Leshem Choshen , Yoon Kim , Jacob Andreas

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data,…

Machine Learning · Computer Science 2024-10-23 Shun Zhang , Zhenfang Chen , Sunli Chen , Yikang Shen , Zhiqing Sun , Chuang Gan

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Machine Learning · Computer Science 2025-10-16 Yuchun Miao , Liang Ding , Sen Zhang , Rong Bao , Lefei Zhang , Dacheng Tao

Reinforcement Learning from Human Feedback (RLHF) has emerged as a important paradigm for aligning large language models (LLMs) with human preferences during post-training. This framework typically involves two stages: first, training a…

Machine Learning · Computer Science 2025-04-08 Wenyuan Xu , Xiaochen Zuo , Chao Xin , Yu Yue , Lin Yan , Yonghui Wu

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…

Machine Learning · Computer Science 2026-04-21 Muhammad Khalifa , Zohaib Khan , Omer Tafveez , Hao Peng , Lu Wang

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong

Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While there has been…

Machine Learning · Computer Science 2022-08-22 Owen Lockwood , Mei Si

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza