“Evaluating Model-Based Planning and Planner Amortization for Continuous Control”, 2021-10-07 (; similar):
There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches. In this paper we attempt to evaluate this intuition on various challenging locomotion tasks.
We take a hybrid approach, combining model predictive control (MPC) with a learned model and model-free policy learning; the learned policy serves as a proposal for MPC. We find that well-tuned model-free agents are strong baselines even for high Degrees of Freedom (DoF) control problems but MPC with learned proposals and models (trained on the fly or transferred from related tasks) can improve performance and data efficiency in hard multi-task/multi-goal settings.
Finally, we show that it is possible to distill a model-based planner into a policy that amortizes the planning computation without any loss of performance.
Videos of agents performing different tasks can be seen at https://sites.google.com/view/mbrl-amortization/home.