English
Related papers

Related papers: Adaptive Action Chunking via Multi-Chunk Q Value E…

200 papers

In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique to improve robotic manipulation abilities. However, a large chunk size reduces the model's…

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…

Machine Learning · Computer Science 2026-05-12 Qiyang Li , Zhiyuan Zhou , Sergey Levine

Offline-to-online reinforcement learning with action chunking eliminates multi-step off-policy bias and enables temporally coherent exploration, but all existing methods use a fixed chunk size across every state. This is suboptimal: near…

Machine Learning · Computer Science 2026-05-08 Nandiraju Gireesh , Yuanliang Ju , He Wang

Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies.…

Robotics · Computer Science 2025-11-07 Yueyang Weng , Xiaopeng Zhang , Yongjin Mu , Yingcong Zhu , Yanjie Li , Qi Liu

In this paper, we study whether model-based reinforcement learning (RL), in particular model-based value expansion, can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL. Model-based value expansion fits an…

Machine Learning · Computer Science 2025-12-10 Kwanyoung Park , Seohong Park , Youngwoon Lee , Sergey Levine

The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…

Computation and Language · Computer Science 2026-03-27 Paulo Roberto de Moura Júnior , Jean Lelong , Annabelle Blangero

Action chunking can improve exploration and value estimation in long horizon reinforcement learning, but makes learning substantially harder since the critic must evaluate action sequences rather than single actions, greatly increasing…

Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs),…

Robotics · Computer Science 2025-12-08 Kevin Black , Manuel Y. Galliker , Sergey Levine

Long-horizon, sparse-reward tasks pose a fundamental challenge for reinforcement learning, since single-step TD learning suffers from bootstrapping error accumulation across successive Bellman updates. Actor-critic methods with action…

Machine Learning · Computer Science 2026-05-13 Qian Chen , Junqiao Zhao , Hongtu Zhou , Hang Yu , Yanping Zhao , Chen Ye , Guang Chen

Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly…

Robotics · Computer Science 2026-03-02 Jiarui Yang , Bin Zhu , Jingjing Chen , Yu-Gang Jiang

In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can…

Machine Learning · Computer Science 2026-03-17 Gwanwoo Song , Kwanyoung Park , Youngwoon Lee

Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrapping mechanism is prone to bootstrapping bias, where the errors in the value…

Machine Learning · Computer Science 2025-12-15 Qiyang Li , Seohong Park , Sergey Levine

Large deep learning models have achieved impressive performance across a range of applications. However, their large memory requirements, including parameter memory and activation memory, have become a significant challenge for their…

Performance · Computer Science 2024-07-10 Xuanlei Zhao , Shenggan Cheng , Guangyang Lu , Jiarui Fang , Haotian Zhou , Bin Jia , Ziming Liu , Yang You

Advantage Learning (AL) seeks to increase the action gap between the optimal action and its competitors, so as to improve the robustness to estimation errors. However, the method becomes problematic when the optimal action induced by the…

Machine Learning · Computer Science 2022-03-23 Zhe Zhang , Yaozhong Gan , Xiaoyang Tan

Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its effects on the learned policy remain inconsistent: some…

Robotics · Computer Science 2025-04-28 Yuejiang Liu , Jubayer Ibn Hamid , Annie Xie , Yoonho Lee , Maximilian Du , Chelsea Finn

Vision-Language-Action (VLA) models demonstrate significant potential for developing generalized policies in real-world robotic control. This progress inspires researchers to explore fine-tuning these models with Reinforcement Learning…

Robotics · Computer Science 2025-08-05 Dongchi Huang , Zhirui Fang , Tianle Zhang , Yihang Li , Lin Zhao , Chunhe Xia

Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address…

Artificial Intelligence · Computer Science 2025-12-29 Yanhao Li , Lu Ma , Jiaran Zhang , Lexiang Tang , Wentao Zhang , Guibo Luo

Recent advances in imitation learning have enabled robots to perform increasingly complex manipulation tasks in unstructured environments. However, most learned policies rely on discrete action chunking, which introduces discontinuities at…

Robotics · Computer Science 2025-06-06 Dongwoo Son , Suhan Park

Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action frequencies, it becomes insufficient when the action…

Robotics · Computer Science 2026-05-26 Kunyun Wang , Yuhang Zheng , Yupeng Zheng , Jieru Zhao , Wenchao Ding

Everyone puts things off sometimes. How can we combat this tendency to procrastinate? A well-known technique used by instructors is to break up a large project into more manageable chunks. But how should this be done best? Here we study the…

Computer Science and Game Theory · Computer Science 2023-09-26 Joe Halpern , Aditya Saraf
‹ Prev 1 2 3 10 Next ›