Deep reinforcement learning (RL) has recently shown significant benefits in solving combinatorial optimization (CO) problems, reducing reliance on domain expertise, and improving computational efficiency. However, the field lacks a unified benchmark for easy development and standardized comparison of algorithms across diverse CO problems. To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems. Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configuration of diverse RL algorithms, neural network architectures, inference techniques, and environments. RL4CO allows researchers to seamlessly navigate existing successes and develop their unique designs, facilitating the entire research process by decoupling science from heavy engineering. We also provide extensive benchmark studies to inspire new insights and future work. RL4CO has attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co.

翻译：深度强化学习（RL）最近在解决组合优化（CO）问题方面显示出显著优势，减少了对领域专业知识的依赖，并提高了计算效率。然而，该领域缺乏一个统一的基准，以便于跨多种CO问题进行算法的便捷开发和标准化比较。为填补这一空白，我们引入了RL4CO，这是一个统一且广泛的基准，其库深度覆盖了23种最先进的方法和超过20个CO问题。RL4CO基于高效的软件库和最佳实现实践构建，具有模块化实现和灵活配置多种RL算法、神经网络架构、推理技术和环境的特点。RL4CO使研究人员能够无缝地探索现有成果并开发其独特设计，通过将科学研究与繁重的工程实现解耦，从而促进整个研究过程。我们还提供了广泛的基准研究，以启发新的见解和未来的工作。RL4CO已吸引了该领域的众多研究人员，并在 https://github.com/ai4co/rl4co 开源。