Preprint
Jul 2026
Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training
BiDiRL, a hybrid time-space multiplexing architecture for asynchronous, disaggregated RL designed to reduce resource idleness, is presented, including a hot-switch runtime that enables rapid switching between rollout and training resources with negligible overhead and a static, scheduling-aware planner based on time-performance modeling.
Zhiqiang Tan, Maoxin Wang, Sijie Wang et al.
· 1 citation