面向搜索式学习的可适配事后经验回放
Adaptable Hindsight Experience Replay for Search-Based Learning
AI总结：
本文提出 Adaptable HER 框架，将事后经验回放与 AlphaZero 式搜索学习灵活集成，通过可调整的重新标记目标、策略目标和轨迹选择，在稀疏奖励及方程发现等任务中超越纯监督学习和强化学习。
摘要：
类似 AlphaZero 的蒙特卡洛树搜索系统最初为双人博弈而提出，利用神经网络引导动态平衡探索与利用。这种组合使其同样适用于经典搜索问题。然而，原始方法使用模拟结果训练网络在稀疏奖励环境中存在局限，尤其是在网络尚不能提供引导的早期阶段。事后经验回放（HER）通过将搜索树中不成功的轨迹重新标记为监督学习信号来解决这一问题。我们提出 Adaptable HER（\ours{}），这是一个将 HER 与 AlphaZero 集成的灵活框架，允许轻松调整 HER 的属性，例如重新标记的目标、策略目标和轨迹选择。我们的实验（包括方程发现）表明，修改 HER 的可能性是有益的，并且超越了纯监督学习或强化学习的性能。
英文摘要：
AlphaZero-like Monte Carlo Tree Search systems, originally introduced for two-player games, dynamically balance exploration and exploitation using neural network guidance. This combination makes them also suitable for classical search problems. However, the original method of training the network with simulation results is limited in sparse reward settings, especially in the early stages, where the network cannot yet give guidance. Hindsight Experience Replay (HER) addresses this issue by relabeling unsuccessful trajectories from the search tree as supervised learning signals. We introduce Adaptable HER (\ours{}), a flexible framework that integrates HER with AlphaZero, allowing easy adjustments to HER properties such as relabeled goals, policy targets, and trajectory selection. Our experiments, including equation discovery, show that the possibility of modifying HER is beneficial and surpasses the performance of pure supervised or reinforcement learning.
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。
