QF3 (Fast Flow RL with Filtered Q-Gradients) is an online off‑policy reinforcement learning algorithm that trains flow policies by combining flow matching with the critic’s action gradient, backpropagated through a one‑step prediction of the flow output. It selectively applies the critic gradient only to action dimensions close to the replay action to ensure reliable updates. QF3 is the first off‑policy flow RL method to train humanoid locomotion policies from scratch and transfer them zero‑shot to hardware, achieving a 10× wall‑clock speedup over the on‑policy FPO++ method, and it can also fine‑tune pretrained flow‑based manipulation policies on ABC‑Sim and Robomimic tasks.
By Chung Min Kim, Brent Yi, David McAllister, Hongsuk Choi, Himanshu Gaurav Singh, Jinkun Cao, Ken Goldberg, Pieter Abbeel, Carmelo Sferrazza, Angjoo Kanazawa
The paper introduces Q‑Learning with Scalar Adjoint Matching (SQAM), a method that replaces expensive per‑step vector–Jacobian products in flow policy fine‑tuning with a closed‑form scalar adjoint that scales the value gradient by flow time. SQAM also incorporates a value penalty on policy‑generated actions, which is shown to be crucial for effective learning. Experiments demonstrate that SQAM outperforms strong baselines on the hardest OGBench domains and improves supervised fine‑tuning on a real bimanual robot with a vision‑language‑action policy.
By Yonghoon Dong, Minsung Yoon, Jaehyuk Kim, Jungwoo Park, Changyeon Kim, Jinwoo Shin
arXiv:2606. 11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.
By Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li, Tobias Springenberg, Kevin Frans, Sergey Levine
arXiv:2603. 13707v3 Announce Type: replace-cross Abstract: Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks.
By Zhaoyuan Gu, Yipu Chen, Zimeng Chai, Alfred Cueva, Thong Nguyen, Yifan Wu, Huishu Xue, Minji Kim, Isaac Legene, Fukang Liu, KyoungMok Kim, Ayan Barula, Yongxin Chen, Ye Zhao
arXiv:2608. 15088v1 Announce Type: cross Abstract: Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the human prior.
By Zihang Wang, Yishan Wang
arXiv:2605. 05172v2 Announce Type: replace-cross Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning.
By Lakshita Dodeja, Ondrej Biza, Shivam Vats, Stephen Hart, Stefanie Tellex, Robin Walters, Karl Schmeckpeper, Thomas Weng
arXiv:2603. 05296v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration.
By Hokyun Im, Andrey Kolobov, Jianlong Fu, Youngwoon Lee
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
By Gong Gao, Weidong Zhao, Xianhui Liu, Ning Jia
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
By Boshu Lei, Kostas Daniilidis, Antonio Loquercio
arXiv:2606. 17551v1 Announce Type: cross Abstract: Iterative generative modeling techniques, such as flow matching, provide powerful tools to model complex behaviors for effective offline reinforcement learning (RL).
By Aditya Oberai, Seohong Park, Sergey Levine
arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.
By Taewook Nam, Junmo Cho, Youngsoo Jang, Sung Ju Hwang
arXiv:2607. 24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process.
By Valerio Belli (UNIROMA, UCL), Valerio Modugno (UCL), Enrico Mingo Hoffman (HUCEBOT), Fabio Amadio (HUCEBOT)