Robuta

https://openreview.net/forum?id=80wh3jjCZf
Large discrete action spaces (LDAS) remain a central challenge in reinforcement learning. Existing solution approaches can handle unstructured LDAS with up to...
discrete actiondynamicneighborhoodconstructionstructured
https://arxiv.org/abs/2508.20072v2
Abstract page for arXiv paper 2508.20072v2: Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
discretediffusionvlabringingaction
https://openreview.net/forum?id=guxVyRKAJY&referrer=%5Bthe%20profile%20of%20Yichen%20Zhu%5D(%2Fprofile%3Fid%3D~Yichen_Zhu1)
Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the...
policy learningmulti taskdiscreteactionspace