# Amazon — Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge

- Company: Amazon (amazon.com)
- Announced: 2026-08-14T16:02:10+00:00
- Category: capability-change
- Subject: Bedrock / Nova
- Models affected: Amazon Nova
- Source: https://aws.amazon.com/blogs/machine-learning/custom-reward-functions-for-multi-turn-reinforcement-learning-with-amazon-nova-forge/
- Record: https://forck.live/items/4163-custom-reward-functions-for-multi-turn-reinforcement-learning-with-amazon-nova

Amazon announces custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge, including a serverless multi-turn RL option now generally available, and describes how to design composite rewards for GRPO.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/custom-reward-functions-for-multi-turn-reinforcement-learning-with-amazon-nova-forge/:

> Nova Forge also offers a serverless multi-turn RL option, now generally available, for teams that prefer not to manage that environment.

---

Record: https://forck.live/items/4163-custom-reward-functions-for-multi-turn-reinforcement-learning-with-amazon-nova
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md