AI Reports · Amazon · 2026-10-23 · Blog / commentary
Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide
Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI trains models on the outcome of an entire multi-step task rather than on labeled steps. This hands-on guide uses Wordle to walk through the full pipeline, from deploying the agent and reward on Amazon Bedrock AgentCore to dataset preparation, training, and evaluation.