Andreas Krause

Human motion alone, when translated into a shared latent space, unlocks zero-shot generalist humanoid control for locomotion and manipulation tasks.

Value-driven optimistic exploration has historically crumbled under deep network approximations, but diagnosing and repairing failure modes in uncertainty propagation allows pure model-free RL to beat complex model-based exploration baselines.

Non-stationary environments demand RL agents forget the past, or else they'll suffer regret.