English
Related papers

Related papers: MONA: Myopic Optimization with Non-myopic Approval…

200 papers

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

Machine Learning · Computer Science 2025-04-16 Alexander David Goldie , Chris Lu , Matthew Thomas Jackson , Shimon Whiteson , Jakob Nicolaus Foerster

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Yanbei Jiang , Chao Lei , Yihao Ding , Krista Ehinger , Jey Han Lau

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become…

Machine Learning · Computer Science 2026-05-27 Jiacheng Li , Jianchao Tan , Hongtao Xu , Jiaqi Zhang , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai

Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world…

Artificial Intelligence · Computer Science 2025-05-15 Montaser Mohammedalamen , Michael Bowling

In this paper, we reveal that most current efficient multimodal fine-tuning methods are hindered by a key limitation: they are directly borrowed from LLMs, often neglecting the intrinsic differences of multimodal scenarios and even…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yake Wei , Yu Miao , Dongzhan Zhou , Di Hu

In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at…

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…

Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-world visual degradations such as blur, compression artifacts,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Rui Liu , Dian Yu , Haolin Liu , Yucheng Shi , Tong Zheng , Runpeng Dai , Haitao Mi , Pratap Tokekar , Leoweiliang

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite…

Machine Learning · Computer Science 2025-10-06 Adrià López Escoriza , Nicklas Hansen , Stone Tao , Tongzhou Mu , Hao Su

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

In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verbose but less helpful response from the LLMs can often…

Machine Learning · Computer Science 2024-02-13 Lichang Chen , Chen Zhu , Davit Soselia , Jiuhai Chen , Tianyi Zhou , Tom Goldstein , Heng Huang , Mohammad Shoeybi , Bryan Catanzaro

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…

Robotics · Computer Science 2023-03-08 Minttu Alakuijala , Gabriel Dulac-Arnold , Julien Mairal , Jean Ponce , Cordelia Schmid

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Machine Learning · Computer Science 2022-04-19 Carl Qi , Pieter Abbeel , Aditya Grover

Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimodal reward function. This assumption does not always hold…

Machine Learning · Computer Science 2021-10-20 Vivek Myers , Erdem Bıyık , Nima Anari , Dorsa Sadigh

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Machine Learning · Computer Science 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

Machine Learning · Computer Science 2025-09-22 Mirza Farhan Bin Tarek , Rahmatollah Beheshti

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…

Motion cueing algorithms (MCA) are used to control the movement of motion simulation platforms (MSP) to reproduce the motion perception of a real vehicle driver as accurately as possible without exceeding the limits of the workspace of the…