用内部市场机制让智能体分工协作，提升强化学习的效率与适应性。
Market-based Architectures in RL and Beyond
- 将状态分解为多个'商品'轴，实现子智能体专业化分工。
- 相比现有方法，显著提升并行处理能力与任务适应性。
- 适用于大模型协同、动态扩展等前沿场景，实用性强。
市场型智能体指基于内部子智能体市场决定行为的强化学习智能体。本文提出一种新型市场算法，将状态分解为多个称为‘商品’的维度，使子智能体能更专业化并行工作，优于现有市场式RL算法。我们进一步论证该框架可应对当前AI中的诸多挑战，如搜索效率、动态扩展与完整反馈，并指出其可能推广神经网络的计算范式；最后，列举了与大型语言模型结合的多种新颖应用场景，具备即时落地潜力。
原文摘要 · Abstract (English)
Market-based agents refer to reinforcement learning agents which determine their actions based on an internal market of sub-agents. We introduce a new type of market-based algorithm where the state itself is factored into several axes called ``goods'', which allows for greater specialization and parallelism than existing market-based RL algorithms. Furthermore, we argue that market-based algorithms have the potential to address many current challenges in AI, such as search, dynamic scaling and complete feedback, and demonstrate that they may be seen to generalize neural networks; finally, we list some novel ways that market algorithms may be applied in conjunction with Large Language Models for immediate practical applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。