Old School RuneScape comes to PufferLib 5.0 as a reinforcement learning environment

neuroecology · x · 2026-09-15

Developer ValtteriValo announced Old School RuneScape running in reinforcement learning framework PufferLib 5.0, with an accompanying technical article. The banner demo shows the final boss enraged, pummeling the player with near-unavoidable damage while the agent tries to stay behind a moving shield.

OSRS ticks every 600 milliseconds, making it a naturally rich RL environment. The author calls it possibly the coolest project he has worked on, with more to come.

Original post →

More from Research

Research channel →