English
Related papers

Related papers: Misalignment from Treating Means as Ends

200 papers

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…

Computer Vision and Pattern Recognition · Computer Science 2023-02-17 André Susano Pinto , Alexander Kolesnikov , Yuge Shi , Lucas Beyer , Xiaohua Zhai

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…

Machine Learning · Computer Science 2023-10-31 Joey Hong , Kush Bhatia , Anca Dragan

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly…

Machine Learning · Computer Science 2023-01-11 Lev McKinney , Yawen Duan , David Krueger , Adam Gleave

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

Machine Learning · Computer Science 2018-11-20 Jan Leike , David Krueger , Tom Everitt , Miljan Martic , Vishal Maini , Shane Legg

One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function. Any misalignment between the reward and the desired behavior can result…

Machine Learning · Computer Science 2025-10-24 Neta Glazer , Aviv Navon , Aviv Shamsian , Ethan Fetaya

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous…

Machine Learning · Computer Science 2019-02-22 Justin Fu , Anoop Korattikara , Sergey Levine , Sergio Guadarrama

In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's…

Machine Learning · Computer Science 2024-12-11 Julien Roy

AI systems often rely on two key components: a specified goal or reward function and an optimization algorithm to compute the optimal behavior for that goal. This approach is intended to provide value for a principal: the user on whose…

Artificial Intelligence · Computer Science 2021-02-09 Simon Zhuang , Dylan Hadfield-Menell

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking arises, we construct four RL environments with misspecified…

Machine Learning · Computer Science 2022-02-15 Alexander Pan , Kush Bhatia , Jacob Steinhardt

In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the…

Machine Learning · Computer Science 2019-02-13 Nikki Lijing Kuang , Clement H. C. Leung

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

Artificial Intelligence · Computer Science 2025-12-05 Shuyuan Zhang

The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used…

General Economics · Economics 2025-11-12 David Autor , Andrew Caplin , Daniel Martin , Philip Marx

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…

Machine Learning · Computer Science 2025-07-09 Lukas Fluri , Leon Lang , Alessandro Abate , Patrick Forré , David Krueger , Joar Skalse

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. To do this, we need a model of how $\pi$ relates to $R$. In the current literature, the most common models are optimality, Boltzmann…

Machine Learning · Computer Science 2023-03-27 Joar Skalse , Alessandro Abate

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

Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting…

Machine Learning · Computer Science 2025-09-03 Haoze Wu , Cheng Wang , Wenshuo Zhao , Junxian He

Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose…

Neurons and Cognition · Quantitative Biology 2025-09-11 Gaia Molinaro , Anne G. E. Collins

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
‹ Prev 1 2 3 10 Next ›