action-chunking

VLA-Corrector introduces a lightweight detect-and-correct inference framework that adaptively adjusts action horizons in Vision-Language-Action policies without retraining, improving robustness and efficiency in robot manipulation tasks.

PolicyTrim is a reinforcement learning-based post-training framework that improves action chunk utilization by 3× and reduces physical execution steps by 51.4% in Vision-Language-Action models, delivering up to 5.83× deployment speedup.

This paper introduces ACSAC, a reinforcement learning method that uses an adaptive chunk size actor-critic algorithm with a causal Transformer Q-network to handle long-horizon, sparse-reward tasks. It demonstrates state-of-the-art performance on manipulation tasks by dynamically adjusting action chunk sizes based on state-dependent needs.

This paper introduces Adaptive Q-Chunking (AQC), a reinforcement learning method that dynamically selects action chunk sizes to balance reactive control and long-horizon planning. It achieves state-of-the-art results on OGBench and Robomimic, enhancing the performance of large-scale VLA models in robotics tasks.