Manipulation

Qualitative comparison of PPO, FastTD3, SAC, and SMM-AC on the Franka Lift and ANYmal-D Rough sim-to-real tasks

Regularised RL Improves Sim-to-Real Transfer

Preprint

Regularised RL has long promised robustness guarantees, but weakly regularised algorithms like PPO still dominate sim-to-real pipelines. We derive SMM-AC, a continuous-control actor-critic built on the soft mellowmax value function, and show on a Franka arm and an ANYmal-D quadruped that regularisation translates into real sim-to-real gains.