The paper presents a Bayesian deep learning approach for active exploration in model-based reinforcement learning applied to robot manipulation. By improving model calibration and actively selecting transitions that maximize information gain, the method enhances data efficiency during a preliminary exploration phase. Experiments on a realistic robotic arm simulator demonstrate that the approach achieves comparable performance to existing methods while requiring significantly fewer robot executions.
By Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin
arXiv:2603.02935v2 Announce Type: replace
Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task repres...
By Mohammadreza Nakheai, Aidan Scannell, Kevin Luck, Joni Pajarinen
arXiv:2606. 18132v1 Announce Type: new Abstract: Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control.
By Yuan Meng, Bo Wang, Juan de los Rios Ruiz, Xiangtong Yao, Zhenshan Bing, Fuchun Sun, Alois Knoll
PrefO2O introduces an offline-to-online latent preference transfer framework that enables zero‑shot preference‑based reinforcement learning on unseen tasks without human feedback. It learns a task‑invariant latent preference space from limited offline preference data, disentangling transferable preference structures from task‑specific variations. The method uses confidence‑weighted optimal transport to generate reliable pseudo‑preference supervision for online reward adaptation, achieving performance that matches or exceeds traditional PbRL methods trained with real human feedback across various robotic manipulation and locomotion benchmarks.
By Ruiqi Wang, Dezhong Zhao, Xuesu Xiao, Erdem Biyik, Byung-Cheol Min, Guohua Chen
arXiv:2603. 15600v2 Announce Type: replace-cross Abstract: Accurate process supervision remains a critical challenge for long-horizon robotic manipulation.
By Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Yao Mu
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. 18830v1 Announce Type: cross Abstract: Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks.
By Garvit Singla, Uma Maheswari Natarajan, Raghuram Bharadwaj Diddigi
The paper introduces a minimal‑data adaptation regime where a pretrained robot policy learns a new task from a single demonstration followed by autonomous online interaction. It shows that while zero‑shot performance is poor, one demonstration can guide the policy toward coarse task‑following, and identifies key design principles—pretrained VLA representations for sample‑efficient value learning, residual policy learning for corrective behavior, and data‑balancing to avoid exploration collapse. The proposed MiDAS method, combining few‑demonstration behavior cloning with value‑based residual learning over frozen VLA representations, significantly boosts task success on LIBERO, RoboCasa, and a bimanual YAM platform after only a few hours of online interaction.
By Shreyas Kowshik, Sreyas Venkataraman, Leo Wang, Niharika Pant, Max Simchowitz, Aviral Kumar
arXiv:2505. 03296v2 Announce Type: replace-cross Abstract: We present Mixture of Discrete-time Gaussian Processes (MiDiGap), a novel approach for flexible policy representation and imitation learning in robot manipulation.
By Jan Ole von Hartz, Adrian R\"ofer, Joschka Boedecker, Abhinav Valada
The paper introduces AnchorQ, a method that improves sample-efficient reinforcement learning for policy refinement by using flow-reversed action anchors. AnchorQ maps reference behaviors to state-conditioned latent anchors, samples local particles around these anchors, and employs value-guided sampling to explore promising refinements. Experiments on simulated and real-world manipulation tasks show that AnchorQ outperforms state-of-the-art post-training baselines, achieving a 37% higher real-world success rate and 97% greater simulated task throughput within the same interaction budget.
By Carl Qi, Weijun Dong, Xiaojie Wang, Peiyi Chen, Rahul Sajnani, Mingyuan Zhang, Amy Zhang, Jose Barreiros, Manikatan Nambi, Lillian J. Ratliff, Dylan Randle
arXiv:2502. 18447v2 Announce Type: replace Abstract: Existing approaches to reward inference typically assume that humans provide demonstrations according to specific behavior models.
By Will Schwarzer, Jordan Schneider, Philip S. Thomas, Scott Niekum
arXiv:2608.29061v1 Announce Type: new
Abstract: Offline goal-conditioned reinforcement learning (GCRL) aims to learn policies for reaching diverse goals entirely from fixed trajectory data. Long-hori...
By Soohyun Choi, Seonvin Cho, Songnam Hong