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.
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.
Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale across tasks, it must make effe...
arXiv:2609.38178v1 Announce Type: cross Abstract: Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this i...
The paper introduces PARTS, a real‑world subtask reinforcement learning framework that fine‑tunes a pretrained robot policy by focusing on critical bottleneck subtasks while keeping the base policy frozen. It uses agent‑generated selectors and success verifiers to provide local rewards, enabling learning even when full‑task successes are rare. Experiments on bimanual YAM and single‑arm Franka robots show that PARTS raises complete‑task success from 32% to 61% and from 50% to 95%, respectively, with only tens of minutes of real‑world RL rollouts and minimal human intervention.
arXiv:2604.00055v2 Announce Type: replace-cross Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilit...
arXiv:2603.16065v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecke...
arXiv:2608. 09853v1 Announce Type: cross Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from large-scale heterogeneous corpora remains underexplored.
arXiv:2604. 09860v4 Announce Type: replace-cross Abstract: The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing.
arXiv:2610.19129v1 Announce Type: new Abstract: Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily app...
arXiv:2610.20318v1 Announce Type: cross Abstract: Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload...
arXiv:2606. 18247v1 Announce Type: cross Abstract: Robots deployed in the real world should learn from their experience and improve over time.