AWS Publishes Multi-Turn Reinforcement Learning Guide With Wordle Training Results

Daniel Quang and coauthors published a hands-on guide to multi-turn reinforcement learning on Amazon SageMaker AI, reporting that their Wordle training example improved gpt-oss-20b’s held-out solve rate from 61% to 84% when evaluated at serving settings. The authors reported costs of about $339 in training tokens and $79 in runtime usage for the example. The walkthrough uses a Wordle agent hosted on Amazon Bedrock AgentCore and covers deploying the agent and reward, preparing the dataset, training, monitoring in MLflow, and evaluating the trained model. It also describes reward design and failures encountered during training, giving readers a worked example of the pipeline and its practical challenges.

Generated by AI from reports · Updated 2 hours ago

There is not enough continuous observation data to plot a trend yet.