Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch
FIELD NOTES TOPIC

asynchronous optimization

3 notes, newest first.

  1. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note ·

    The paper proposes a new method called Single-rollout Asynchronous Optimization (SAO) for Reinforcement Learning (RL) in post-training large language models (LLMs). SAO aims to improve stability and task effectiveness…

  2. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note ·

    The paper introduces Single-rollout Asynchronous Optimization (SAO), a new approach to reinforcement learning (RL) aimed at post-training large language models (LLMs). SAO addresses stability and off-policy challenges…

  3. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note ·

    In this paper, the authors introduce Single-rollout Asynchronous Optimization (SAO), a new approach to reinforcement learning (RL) for post-training large language models (LLMs). SAO aims to improve training stability…