English
Related papers

Related papers: EfficientZero V2: Mastering Discrete and Continuou…

200 papers

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Zerun Wang , Jiafeng Mao , Xueting Wang , Toshihiko Yamasaki

In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more data than previous approaches. This extensive dataset…

Robotics · Computer Science 2025-07-02 Yating Wang , Haoyi Zhu , Mingyu Liu , Jiange Yang , Hao-Shu Fang , Tong He

Two-time-scale optimization is a framework introduced in Zeng et al. (2024) that abstracts a range of policy evaluation and policy optimization problems in reinforcement learning (RL). Akin to bi-level optimization under a particular type…

Optimization and Control · Mathematics 2026-01-21 Sihan Zeng , Thinh T. Doan

Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert…

Machine Learning · Computer Science 2023-09-13 Loris Di Natale , Bratislav Svetozarevic , Philipp Heer , Colin N. Jones

Code efficiency is a fundamental aspect of software quality, yet how to harness large language models (LLMs) to optimize programs remains challenging. Prior approaches have sought for one-shot rewriting, retrieved exemplars, or prompt-based…

Software Engineering · Computer Science 2026-03-31 Zimu Wang , Yuling Shi , Mengfan Li , Zijun Liu , Jie M. Zhang , Chengcheng Wan , Xiaodong Gu

While large language models (LLMs) demonstrate reasonable zero-shot capability across many downstream tasks, fine-tuning is a common practice to improve their performance. However, a task's data efficiency--i.e., the number of fine-tuning…

Machine Learning · Computer Science 2026-01-01 Gyung Hyun Je , Colin Raffel

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences.…

Machine Learning · Computer Science 2020-01-15 William Whitney , Rajat Agarwal , Kyunghyun Cho , Abhinav Gupta

Deep Reinforcement Learning (RL) can yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of…

Machine Learning · Computer Science 2024-11-20 Jonas Eschmann , Dario Albani , Giuseppe Loianno

The field of keypoint extraction, which is essential for vision applications like Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM), has evolved from relying on handcrafted methods to leveraging deep learning…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Haodi Yao , Fenghua He , Ning Hao , Chen Xie

Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL…

Robotics · Computer Science 2024-09-20 Jesse Zhang , Minho Heo , Zuxin Liu , Erdem Biyik , Joseph J Lim , Yao Liu , Rasool Fakoor

When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as…

Machine Learning · Computer Science 2019-10-10 Vibhavari Dasagi , Jake Bruce , Thierry Peynot , Jürgen Leitner

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…

Machine Learning · Computer Science 2025-10-20 Shashank Gupta

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current RL pipelines often suffer from training inefficiencies…

Machine Learning · Computer Science 2026-03-04 Linghao Zhu , Yiran Guan , Dingkang Liang , Jianzhong Ju , Zhenbo Luo , Bin Qin , Jian Luan , Yuliang Liu , Xiang Bai

Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to…

Machine Learning · Computer Science 2026-03-23 Chengxuan Lu , Shukuan Wang , Yanjie Li , Wei Liu , Shiji Jin , Fuyuan Qian , Peiming Li , Baigui Sun , Yang Liu

Reinforcement learning has been demonstrated as a flexible and effective approach for learning a range of continuous control tasks, such as those used by robots to manipulate objects in their environment. But in robotics particularly,…

Robotics · Computer Science 2022-10-25 Tuluhan Akbulut , Max Merlin , Shane Parr , Benedict Quartey , Skye Thompson

This position paper proposes a fresh look at Reinforcement Learning (RL) from the perspective of data-efficiency. Data-efficient RL has gone through three major stages: pure on-line RL where every data-point is considered only once, RL with…

Machine Learning · Computer Science 2021-08-24 Martin Riedmiller , Jost Tobias Springenberg , Roland Hafner , Nicolas Heess

Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several…

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse…

Robotics · Computer Science 2020-02-28 Ke Lin , Liang Gong , Xudong Li , Te Sun , Binhao Chen , Chengliang Liu , Zhengfeng Zhang , Jian Pu , Junping Zhang

In heterogeneous multi-task decision-making, tasks not only exhibit diverse observation and action spaces but also vary substantially in their underlying complexities. While conventional multi-task world models like UniZero excel in…

Machine Learning · Computer Science 2026-03-09 Yuan Pu , Yazhe Niu , Jia Tang , Junyu Xiong , Shuai Hu , Hongsheng Li