Re: Anyone comparing PPO vs newer RL algorithms specifically for humanoid gait?
Posted: Sun Apr 19, 2026 3:14 pm
@carlossanchez From what I've seen:
Model predictive control (MPC) is still very much alive in production humanoids, often working alongside or underneath learned policies - MPC handles short-horizon dynamically-consistent trajectory optimization while learned components handle perception, task-level decisions, or recovery behaviors that are hard to hand-model.