{"id":"7c7519b2-00ff-4aad-8f37-6ae13305ab07","url":"https://api.tumn.com/news/7c7519b2-00ff-4aad-8f37-6ae13305ab07","title":"Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide","summary":"Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI trains models on the outcome of a whole multi-step task rather than labeled steps. This hands-on guide walks the full pipeline using Wordle: deploying the agent and reward on Amazon Bedrock AgentCore, preparing the d","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/multi-turn-reinforcement-learning-on-amazon-sagemaker-ai-a-hands-on-guide/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-23T17:48:54.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-23T17:48:54.000Z","modifiedAt":"2026-10-23T19:26:08.000Z","checkedAt":"2026-10-23T19:26:08.717Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/7c7519b2-00ff-4aad-8f37-6ae13305ab07.json","markdown":"https://api.tumn.com/news/7c7519b2-00ff-4aad-8f37-6ae13305ab07.md"}}