Shweta Verma
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller models and complex coding tasks.
This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller models and complex coding tasks.
Papers
Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…