When would you prefer DMPO over SAC for continuous control if real-world deployment is not the issue?
Hi everyone, I have been reading about Distributional Maximum a Posteriori Policy Optimization (DMPO), especially in the context of the DeepMind bipedal robot soccer paper, and I am trying to understand when one would practically prefer it over SAC. My current understanding is: SAC is a strong off-policy continuous-control baseline. It directly optimizes the actor using an entropy-regularized objective. It is widely implemented, easier to find baselines for, and generally very strong in simulation. On the other hand, […]