Publications#
This page lists papers and technical reports associated with RLinf. Detailed publication pages (with results and quickstart links) are linked below.
Detailed publication pages#
Publication |
Focus |
Paper |
|---|---|---|
Self-supervised temporal ensemble advantage modeling for real-world robot learning. |
||
Unified system for real-world online policy learning. |
||
Unified framework for VLA+RL training. |
||
Reinforcement learning-based sim-real co-training for VLA models. |
||
Flexible and efficient RL system. |
||
Flexible and dynamic scheduling for large-scale RL training. |
||
Online RL fine-tuning for flow-based VLA models. |
||
World model-based RL fine-tuning for VLA policies. |
||
Exploring width scaling for broad information seeking via multi-agent reinforcement learning. |