基于学习队友模型的分散式MCTS
Decentralized MCTS via Learned Teammate Models
摘要：
分散在线规划可以是一个有吸引力的合作多智能体系统的范例，由于改进的可扩展性和鲁棒性。这种方法的一个关键困难在于对其他代理人的决策做出准确的预测。在本文中，我们提出了一个可训练的在线分散规划算法的基础上分散的蒙特卡罗树搜索，结合模型的队友从以前的情节运行。通过只允许一个代理，以适应其模型在一个时间，在理想的政策近似的假设下，我们的方法的连续迭代保证改善联合政策，并最终导致收敛到一个纳什均衡。我们通过在[Claes et al.，2015年]。我们表明，深度学习和卷积神经网络可以用来产生精确的策略近似器，利用问题的空间特征，并且所提出的算法提高了基线规划性能，特别是具有挑战性的域配置。
英文摘要：
Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness. A key difficulty of such approach lies in making accurate predictions about the decisions of other agents. In this paper, we present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search, combined with models of teammates learned from previous episodic runs. By only allowing one agent to adapt its models at a time, under the assumption of ideal policy approximation, successive iterations of our method are guaranteed to improve joint policies, and eventually lead to convergence to a Nash equilibrium. We test the efficiency of the algorithm by performing experiments in several scenarios of the spatial task allocation environment introduced in [Claes et al., 2015]. We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators which exploit the spatial features of the problem, and that the proposed algorithm improves over the baseline planning performance for particularly challenging domain configurations.
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。
