Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing
Miao Rang, Zhenni Bi, Hang Zhou +6
Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, t…
cs.LG2020
Soft policy optimization using dual-track advantage estimator
Yubo Huang, Xuechun Wang, Luobao Zou +2
In reinforcement learning (RL), we always expect the agent to explore as many states as possible in the initial stage of training and exploit the explored information in the subseq…