Student First Author: yes
Keywords: model predictive control, policy search, reinforcement learning, approximate inference
TL;DR: Sample-based MPC is a form for Bayesian inference. Use Gaussian processes for smooth actions and choose the temperature to have a healthy effective sample size.
Abstract: Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models, and learning from data. These methods scale to high-dimensional spaces and are effective at the non-convex optimization often seen in robot learning. We look at sample-based methods from the perspective of inference-based control, specifically posterior policy iteration. From this perspective, we highlight how Gaussian noise priors produce rough control actions that are unsuitable for physical robot deployment. Considering smoother Gaussian process priors, as used in episodic reinforcement learning and motion planning, we demonstrate how smoother model predictive control can be achieved using online sequential inference. This inference is realized through an efficient factorization of the action distribution, and novel means of optimizing the likelihood temperature for to improve importance sampling accuracy. We evaluate this approach on several high-dimensional robot control tasks, matching the sample efficiency of prior heuristic methods while also ensuring smoothness. Simulation results can be seen at monte-carlo-ppi.github.io.
Supplementary Material: zip