ReleaseBytes
gcp Google Cloud release notes ·

Google Cloud Console Adds RL Fine-tuning for Gemini Models

aipreviewdata-scientist
feature

Google Cloud now offers reinforcement learning (RL) fine-tuning for Gemini models directly within the Google Cloud console. This new capability allows users to create, monitor, and test RL fine-tuning jobs for their models in a unified environment. It includes features for configuring Python code or model-based reward functions, testing reward logic against sample prompts, and tracking training metrics in real-time. This functionality is currently available in Preview, enabling data scientists to iteratively improve Gemini models within a managed console environment.

Features (1) ›
  • Gemini Enterprise Agent Platform Reinforcement learning fine-tuning in the Google Cloud console (Preview)

    Reinforcement learning fine-tuning in the Google Cloud console (Preview) You can create, monitor, and test reinforcement learning fine-tuning jobs for Gemini models in the Google Cloud console ( Preview ). From the Models > Tuning page, you can configure Python code or model-based reward functions, test reward logic against sample prompts before launching a job, track training and evaluation metrics in real time, and test tuned checkpoints in Agent Studio. For more information, see Quick start: Reinforcement learning fine-tuning using the console .

    PreviewQuick start: Reinforcement learning fine-tuning using the console
Read the original announcement →

https://docs.cloud.google.com/release-notes#September_15_2026

Related releases