避免已知：GFlowNets的发散轨迹平衡
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
AI总结：
ACE通过引入专门训练的探索GFlowNet，有效提升GFlowNets在探索新颖和高概率区域时的效率和准确性。
摘要：
生成流网络（GFlowNets）是一类灵活的近似采样器，训练目的是生成具有概率与奖励函数成比例的离散和组合对象。然而，学习效率受到模型在训练过程中快速探索多样化高概率区域的能力的限制。为缓解这一问题，近期的研究重点是通过好奇心驱动搜索和自监督随机网络蒸馏来激励探索未访问和有价值的态。这些方法倾向于在状态空间中已经近似良好的区域浪费样本。在此背景下，我们提出了自适应互补探索（ACE），一种用于有效探索新颖和高概率区域的原理性算法，当学习GFlowNets时。为此，ACE引入了一个专门训练的探索GFlowNet，旨在搜索由传统GFlowNet未充分探索的区域中的高奖励态，该算法学会从目标分布中采样。通过广泛的实验，我们证明ACE在目标分布的近似准确性和发现多样化高奖励态的比率方面显著优于先前的工作。
英文摘要：
Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the model's ability to rapidly explore diverse high-probability regions during training. To mitigate this issue, recent works have focused on incentivizing the exploration of unvisited and valuable states via curiosity-driven search and self-supervised random network distillation, which tend to waste samples on already well-approximated regions of the state space. In this context, we propose Adaptive Complementary Exploration (ACE), a principled algorithm for the effective exploration of novel and high-probability regions when learning GFlowNets. To achieve this, ACE introduces an exploration GFlowNet explicitly trained to search for high-reward states in regions underexplored by the canonical GFlowNet, which learns to sample from the target distribution. Through extensive experiments, we show that ACE significantly improves upon prior work in terms of approximation accuracy to the target distribution and discovery rate of diverse high-reward states.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
