
Enhancing the training effectiveness of Generative Flow Networks (GFlowNets) through local search to improve mode seeking and average reward performance.


coremsg

local-search-gflownets-enhancing-gflownets-training-with-local-search


Local Search GFlowNets: Enhancing GFlowNets Training with Local Search


title_rewrite


Local Search GFlowNets enhances training effectiveness by leveraging local search in object space, improving mode seeking and average reward performance.


local-search-gflownets-enhancing-gflownet-training-with-local-search


Local Search GFlowNets: Enhancing GFlowNet Training with Local Search



Dynamic Backtracking GFN (DB-GFN) enhances the adaptability of GFlowNet decision-making through a reward-based dynamic backtracking mechanism, enabling more efficient exploration of the sampling space and generating higher-quality samples.


dynamic-backtracking-in-gflownet-enhancing-decision-making-with-reward-guided-exploration


Dynamic Backtracking in GFlowNet: Enhancing Decision-Making with Reward-Guided Exploration
