asynchronous-training

Tag

Cards List
#asynchronous-training

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

arXiv cs.LG · 2026-06-29 Cached

This paper introduces Retroactive Advantage Correction (RAC), a closed-form bias correction method for delay-aware RLHF that handles asynchronous reward signals by queuing and reinjecting delayed rewards with a V-trace-style clipped residual update.

0 favorites 0 likes
#asynchronous-training

AsyncOPD: How Stale Can On-Policy Distillation Be?

arXiv cs.LG · 2026-06-24 Cached

This paper presents AsyncOPD, a fully asynchronous on-policy distillation pipeline for LLMs, systematically studying the effects of stale-policy data and proposing estimator designs that improve training throughput by 1.6-3.8x while maintaining comparable accuracy.

0 favorites 0 likes
#asynchronous-training

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Hugging Face Daily Papers · 2026-05-12 Cached

This paper addresses the missing old logits problem in asynchronous reinforcement learning for LLMs, proposing exact and approximate correction methods to improve training stability and performance.

0 favorites 0 likes
← Back to home

Submit Feedback