NUS Proposes WM-PPO: World-Model-Predicted Successor States Improve PPO Policy Learning
NationalUniversityofSingapore · hf · 2026-11-11
Researchers at the National University of Singapore propose WM-PPO, which combines a world model with PPO's critic. The world model predicts successor states for candidate actions, and the critic values them to create auxiliary policy advantages and value targets, improving task success without privileged information. One world model feeds two learning channels — real-interaction returns via PPO-GAE and predicted candidate transitions via an auxiliary policy channel — before a PPO-Clip update.
More from Embodied
- CoRL 2026's wildest moments: 'Why do you care about delay?' and 'haptic doesn't matter' — breadli428 · 2026-11-11
- JKU Linz's new Institute for Machine Intelligence hires 2 PhD students in robot learning, deadline in a week — HildeKuehne · 2026-11-11
- Darpinian: Tesla should wait for the AI5 chip before scaling Cybercab production — Darpinian · 2026-11-11
- Maestro paper: cheap Gemini 2.5 beats π₀.5 baselines at zero-shot robot control — dineshjayaraman · 2026-11-11
- OpenDDE: open-source all-atom drug discovery engine hits 51% on hard antibody-antigen benchmark — teortaxesTex · 2026-11-11
- Tesla demos Optimus walking inside a world model at CoRL, real policy in control — Scobleizer · 2026-11-11