---
title: "Amazon SageMaker AI launches multi-turn reinforcement learning for AI agent model customization"
url: https://daily.dev/posts/amazon-sagemaker-ai-launches-multi-turn-reinforcement-learning-for-ai-agent-model-customization-zoa9pgyuq
source_url: https://aws.amazon.com/about-aws/whats-new/2026/06/multi-turn-reinforcement-learning-on-sagemaker-ai
type: article
source: "AWS"
published: 2026-06-03T16:07:21.342Z
updated: 2026-06-03T16:07:43.555Z
tags: ["aws", "ai-agents", "reinforcement-learning", "amazon-bedrock"]
reading_time: 2
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Amazon SageMaker AI launches multi-turn reinforcement learning for AI agent model customization

**[AWS](https://daily.dev/sources/aws)** · 2 min read · 0 upvotes · 0 comments

## Summary

Amazon SageMaker AI now supports multi-turn reinforcement learning (RL), a serverless model customization technique for fine-tuning models on multi-step agentic tasks. It extends existing fine-tuning options (RLVR, RLAIF) by training models against custom agent environments and rewarding full decision sequences across a task. This enables smaller, lower-cost models to match or exceed larger general-purpose models on targeted workloads. SageMaker manages the full training loop including rollout orchestration, trajectory collection, and checkpoint management. It integrates with Amazon Bedrock AgentCore Runtime, EKS, EC2, Fargate, and other infrastructure. Built-in MLflow tracking and evaluation metrics (reward, pass@k, trajectory) are included. The feature is fully serverless with pay-per-token pricing, available via SageMaker Studio and the Python SDK, supporting models like Qwen 3.6 27B, Nova Lite 2.0, GPT-OSS-20B, and Gemma 31B.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://aws.amazon.com/about-aws/whats-new/2026/06/multi-turn-reinforcement-learning-on-sagemaker-ai>

## Similar posts on daily.dev

- [New serverless model customization capability in Amazon SageMaker AI](https://daily.dev/posts/new-serverless-model-customization-capability-in-amazon-sagemaker-ai-i5g9gpni5) · AWS · 1 upvotes · 0 comments
- [Amazon SageMaker AI launches AI agent experience for model customization](https://daily.dev/posts/amazon-sagemaker-ai-launches-ai-agent-experience-for-model-customization-cre7g5z8k) · AWS · 1 upvotes · 0 comments

---

Tags: [#aws](https://daily.dev/tags/aws), [#ai-agents](https://daily.dev/tags/ai-agents), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock)

[View this post on daily.dev](https://daily.dev/posts/amazon-sagemaker-ai-launches-multi-turn-reinforcement-learning-for-ai-agent-model-customization-zoa9pgyuq)