Evaluating model-based planning and planner amortization for continuous control
This work addresses data efficiency challenges for robotics and reinforcement learning practitioners, presenting incremental improvements over existing hybrid methods.
The paper tackles the problem of improving data efficiency in continuous control tasks by evaluating model-based planning and planner amortization, finding that combining model predictive control with learned models and policies can significantly enhance performance and data efficiency in challenging multi-task settings, and demonstrating that a planner can be distilled into a policy without performance loss.
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 DoF control problems but MPC with learned proposals and models (trained on the fly or transferred from related tasks) can significantly improve performance and data efficiency in hard multi-task/multi-goal settings. Finally, we show that it is possible to distil 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.