arXiv Machine Learning August 14, 2026 By C. F. Maximilian Nagy, Onur Celik, Emiliyan Gospodinov, Florian Seligmann, Weiran Liao, Aryan Kaushik, Gerhard Neumann

SEAR: Sample Efficient Action Chunking Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2603. 01891v2 Announce Type: replace Abstract: Action chunking improves exploration and accelerates value propagation in long-horizon reinforcement learning, but naively applying off-policy methods to the temporally extended action space at reduced decision frequency offsets these gains, leading to poor sample efficiency.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 24

Offline RL with Hierarchical Action Chunking

arXiv:2607. 20834v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets.

By Ahad Jawaid

rag reinforcement-learning

Hugging Face Trending Papers

Jul 23

Offline RL with Hierarchical Action Chunking

Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound through long chains of bootstrapped Bellman backups.

rag reinforcement-learning

arXiv Machine Learning

Jun 16

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

arXiv:2502. 19544v3 Announce Type: replace Abstract: Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL).

By Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter B\"uchler, Arno Solin, Juho Kannala, Joni Pajarinen

reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Jun 8

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

arXiv:2503. 03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets.

By Dong Tian, Onur Celik, Gerhard Neumann

llms rag reinforcement-learning benchmarks

arXiv Machine Learning

Jul 31

TAPO: Transition-Aware Policy Optimization for LLM Agents

arXiv:2607. 27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents.

By Cong Li, Peixi Peng, Yisen Zhao, Xinyu Hu, Shudong Liu, Zhan Su, Zhuojian Li

llms agents reinforcement-learning

arXiv AI

Jul 7

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

arXiv:2607. 04265v1 Announce Type: cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception, and contact-dynamics errors in real-world precision tasks, often failing in the final few millimeters of alignment or insertion.

By Angen Ye, Weijie Ke, Xiaofeng Wang, Xinze Chen, Chaojun Ni, Guosheng Zhao, Boyuan Wang, Zheng Zhu, Junjie Xie, Dapeng Zhang

reinforcement-learning robotics safety

Related stories

Offline RL with Hierarchical Action Chunking

Offline RL with Hierarchical Action Chunking

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

TAPO: Transition-Aware Policy Optimization for LLM Agents

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models