![[2606.01865] Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections](/static/img/curated/desks/afbytes-tech.png)
[2606.01865] Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
Abstract page for arXiv paper 2606.01865: Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
America Forever Bytes
rl · AFBytes
Other
rl
Recent coverage
[2606.00913] Bandit Simulation for Average Reward Inference
Abstract page for arXiv paper 2606.00913: Bandit Simulation for Average Reward Inference
[2606.02398] A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
Abstract page for arXiv paper 2606.02398: A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
[2606.01636] Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
Abstract page for arXiv paper 2606.01636: Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
[2605.28184] Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
Abstract page for arXiv paper 2605.28184: Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
[2605.28276] Commit to the Bit: Reactive Reinforcement Learning Done Right
Abstract page for arXiv paper 2605.28276: Commit to the Bit: Reactive Reinforcement Learning Done Right
[2605.28127] Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
Abstract page for arXiv paper 2605.28127: Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning