Improving GFlowNets with Monte Carlo Tree Search

TL;DR

This paper enhances Generative Flow Networks by integrating Monte Carlo Tree Search, leading to improved training efficiency and higher quality object generation in discrete spaces.

Contribution

It adapts the MENTS algorithm for GFlowNets, enabling better planning during training and inference, which was not previously explored.

Findings

Improved sample efficiency during GFlowNet training.

Enhanced generation fidelity of pre-trained GFlowNets.

Effective integration of MCTS with GFlowNets.

Abstract

Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to construct objects step by step. Recent studies have revealed strong connections between GFlowNets and entropy-regularized reinforcement learning. Building on these insights, we propose to enhance planning capabilities of GFlowNets by applying Monte Carlo Tree Search (MCTS). Specifically, we show how the MENTS algorithm (Xiao et al., 2019) can be adapted for GFlowNets and used during both training and inference. Our experiments demonstrate that this approach improves the sample efficiency of GFlowNet training and the generation fidelity of pre-trained GFlowNet models.