Multi-agent Reinforcement Learning Accelerated MCMC on Multiscale Inversion Problem

Understand

In this work, we propose a multi-agent actor-critic reinforcement learning (RL) algorithm to accelerate the multi-level Monte Carlo Markov Chain (MCMC) sampling algorithms.

• The policies (actors) of the agents are used to generate the proposal in the MCMC steps; and the critic, which is centralized, is in charge of estimating the long term reward.
• We verify our proposed algorithm by solving an inverse problem with multiple scales.
• There are several difficulties in the implementation of this problem by using traditional MCMC sampling.