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.
More from Research
- Five pharma companies fine-tune OpenFold3 federated, lifting ligand-pose accuracy from 29% to 47% — AllThingsApx · 2026-09-15
- Replacing a Rust Enum with a 64-bit Word Made This Interpreter 17% Faster — blaizedsouza · 2026-09-15
- Research advice: imagine your line of work succeeding in 5 years to structure it today — abursuc · 2026-09-15
- RareGap Atlas maps 11,460 rare diseases into 4,073 queryable intervention hypotheses — RichardsonDx · 2026-09-15
- Princeton eval finds reasoning models fail structurally equivalent task variants, lacking systematicity — princetonu · 2026-09-15
- TREVIS learns sparse decision trees via transformer variational auto-encoders — Giacomo Fidone · 2026-09-15