ICML Workshop 2024 Improving GFlowNets with Monte Carlo Tree Search

  1. Photo Nikita Morozov Nikita Morozov
  2. Photo Daniil Tiapkin Daniil Tiapkin
  3. Photo Sergey Samsonov Sergey Samsonov
  4. Photo Alexey Naumov Alexey Naumov
  5. Photo Dmitry Vetrov Dmitry Vetrov

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.

paper