arXiv:2605. 27095v2 Announce Type: replace Abstract: Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions.
arXiv:2510. 09222v3 Announce Type: replace Abstract: Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors.
The paper proposes a method to train efficient multi‑task manipulation policies by distilling knowledge from single‑task Conditional Flow Matching (CFM) experts. Instead of training separate models for each task, the authors transfer the experts’ learned velocity fields into a shared policy, combining this distillation signal with the original CFM objective. Experiments on RLBench demonstrate that this approach improves multi‑task performance while keeping the model size fixed, avoiding the need for larger capacity or performance drops seen with naive concatenated training.
arXiv:2607. 29617v1 Announce Type: cross Abstract: Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model training.
arXiv:2608.22364v1 Announce Type: new Abstract: World action models (WAMs) couple visual future prediction with robot action generation, but accelerated students can lose task capabilities during dis...
arXiv:2606. 27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
arXiv:2606. 25800v1 Announce Type: new Abstract: Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies.
arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.
Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies. Although self-distillation can in principle provide denser training signals, we find that text-based privileged teachers conditioned on demonstrations, retrieved experiences, or high-level plans are ineffective for VLA adaptation, exposing a modality gap between symbolic guidance and low-level robot actions.
The paper introduces On‑Policy Warmup (OPW), a teacher‑guided training stage where a student agent learns from a teacher on its own interaction trajectories before switching to reinforcement learning with verifiable rewards (RLVR). OPW differs from traditional imitation by focusing on states generated by the student’s own decisions, including imperfect actions and recovery situations. The authors provide a theoretical link between on‑policy reverse‑KL distillation and trajectory‑level distribution matching, showing that, under a competent teacher and low distillation loss, OPW can lower bound initial verifier success and reduce reward‑discovery complexity, thereby accelerating RLVR performance.
arXiv:2607. 17760v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations.
arXiv:2608. 09233v1 Announce Type: new Abstract: Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-training, which may cause conflicts among task-specific optimization objectives.