arXiv:2603. 05296v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration.
arXiv:2607. 08877v1 Announce Type: cross Abstract: Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks.
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.
arXiv:2611.07275v1 Announce Type: cross Abstract: Pre-trained diffusion and flow policies have emerged as powerful backbones for robotics, yet adapting them to novel data via reinforcement learning (...
arXiv:2606. 01151v1 Announce Type: new Abstract: Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift.
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
arXiv:2606. 17408v1 Announce Type: cross Abstract: Generative robot policies typically begin action generation from an observation-independent standard Gaussian distribution, leaving the choice of source distribution underexplored.
arXiv:2607. 10369v1 Announce Type: cross Abstract: Flow-matching policies have emerged as an effective policy parameterization for robot learning.
The paper investigates the LeWorldModel (LeWM) and its Sketched Isotropic Gaussian Regularizer (SIGReg), showing that the original Raw LeWM objective biases variance toward temporally persistent components, which suppresses residual variance and hampers robot state decodability. By applying SIGReg specifically to temporally centered residuals, the authors decouple persistent and residual variance allocation, improving representation quality. On the LIBERO benchmark, this adjustment boosts downstream policy success on the Goal suite by 1.66× and raises overall success rates from 63.6% to 83.8%, outperforming Diffusion Policy and pretrained OpenVLA without external pretraining.
Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusion- and flow-matching robot policies lack tractable likelihoods, limiting their use in likelihood-based offline RL post-training.
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv:2608. 20208v1 Announce Type: new Abstract: Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction.