English
Related papers

Related papers: Misalignment from Treating Means as Ends

200 papers

As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge. A key concern is \textit{instrumental convergence}, where an AI system, in optimizing for a given…

Artificial Intelligence · Computer Science 2025-02-19 Yufei He , Yuexin Li , Jiaying Wu , Yuan Sui , Yulin Chen , Bryan Hooi

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Machine Learning · Computer Science 2024-02-05 Nathan Lambert , Roberto Calandra

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans

Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually…

Artificial Intelligence · Computer Science 2021-01-20 Rachel Freedman , Rohin Shah , Anca Dragan

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a…

Machine Learning · Computer Science 2024-11-26 Joar Skalse , Alessandro Abate

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…

Artificial Intelligence · Computer Science 2023-02-10 Malek Mechergui , Sarath Sreedharan

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function. However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and…

Machine Learning · Computer Science 2025-05-27 Rushit N. Shah , Nikolaos Agadakos , Synthia Sasulski , Ali Farajzadeh , Sanjiban Choudhury , Brian Ziebart

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Computation and Language · Computer Science 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo

In model-based reinforcement learning it is typical to decouple the problems of learning the dynamics model and learning the reward function. However, when the dynamics model is flawed, it may generate erroneous states that would never…

Machine Learning · Computer Science 2018-06-12 Erik Talvitie

Reinforcement learning has emerged as an important approach for autonomous driving. A reward function is used in reinforcement learning to establish the learned skill objectives and guide the agent toward the optimal policy. Since…

Robotics · Computer Science 2026-03-05 Ahmed Abouelazm , Jonas Michel , J. Marius Zoellner

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Machine Learning · Computer Science 2025-06-16 Megan Tjandrasuwita , Chanakya Ekbote , Liu Ziyin , Paul Pu Liang

Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question…

Artificial Intelligence · Computer Science 2021-03-29 Tom Everitt , Marcus Hutter , Ramana Kumar , Victoria Krakovna

Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research. However, even with the recognition of…

Artificial Intelligence · Computer Science 2024-11-01 Malek Mechergui , Sarath Sreedharan

Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited…

Computation and Language · Computer Science 2026-05-07 Gayane Ghazaryan , Esra Dönmez

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…

Two core challenges of alignment are 1) scalable oversight and 2) accounting for the dynamic nature of human values. While solutions like recursive reward modeling address 1), they do not simultaneously account for 2). We sketch a roadmap…

Artificial Intelligence · Computer Science 2025-03-19 Florian Mai , David Kaczér , Nicholas Kluge Corrêa , Lucie Flek

We study reinforcement learning from human feedback under misspecification. Sometimes human feedback is systematically wrong on certain types of inputs, like a broken compass that points the wrong way in specific regions. We prove that when…

Artificial Intelligence · Computer Science 2025-09-16 Madhava Gaikwad

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

Inverse reinforcement learning (IRL) aims to infer an agent's preferences (represented as a reward function $R$) from their behaviour (represented as a policy $\pi$). To do this, we need a behavioural model of how $\pi$ relates to $R$. In…

Machine Learning · Computer Science 2024-03-12 Joar Skalse , Alessandro Abate