Skip to content

Overview
Setup Guide
- Prepare agent for RL
- Training backends
Examples
- Overview
- Strands Agents on AgentCore
Blog
- Overview
- Training multi-step agents with RL
API Reference
- Core
- Backends
  - slime
    
    SlimeRunner
Troubleshooting
- Training backends
  - slime

Blog

Notes, deep dives, and experimental results from training agents with reinforcement learning on Bedrock AgentCore Runtime.

Training multi-step agents on AgentCore Runtime with reinforcement learning — an end-to-end system for online RL on multi-step agents, with results from training on two long-horizon benchmarks: MigrationBench (Java code-migration) and OfficeBench (office automation).