多主体强化学习协作策略研究 内容简介

多主体的研究与应用是近年来备受关注的热点领域，多主体强化学习理论与方法、多主体协作策略的研究是该领域重要研究方向，其理论和应用价值极为广泛，备受广大从事计算机应用、人工智能、自动控制、以及经济管理等领域研究者的关注。本书清晰地介绍了多主体、强化学习及多主体协作等基本概念和基础内容，明确地阐述了有关多主体强化学习、协作策略研究的发展过程及*新动向，深入地探讨了多主体强化学习与协作策略的理论与方法，具体地分析了多主体强化学习与协作策略在相关研究领域的应用方法。全书系统脉络清晰、基本概念清楚、图表分析直观，注重内容的体系化和实用性。通过本书的阅读和学习，读者即可掌握多主体强化学习及协作策略的理论和方法，更可了解在实际工作中应用这些研究成果的手段。 本书可作为从事计算机应用、人工智能、自动控制、以及经济管理等领域研究者的学习和阅读参考，同时高等院校相关专业研究生以及人工智能爱好者也可从中获得借鉴。

多主体强化学习协作策略研究 本书特色

多主体的研究与应用是近年来备受关注的热点领 域，多主体强化学习理论与方法、多主体协作策略的 研究是该领域重要研究方向，其理论和应用价值极为 广泛，备受广大从事计算机应用、人工智能、自动控 制、以及经济管理等领域研究者的关注。孙若莹、赵 刚所著的《多主体强化学习协作策略研究》清晰地介 绍了多主体、强化学习及多主体协作等基本概念和基 础内容，明确地阐述了有关多主体强化学习、协作策 略研究的发展过程及*新动向，深入地探讨了多主体 强化学习与协作策略的理论与方法，具体地分析了多 主体强化学习与协作策略在相关研究领域的应用方法 。 全书系统脉络清晰、基本概念清楚、图表分析直 观，注重内容的体系化和实用性。通过本书的阅读和 学习，读者即可掌握多主体强化学习及协作策略的理 论和方法，更可了解在实际工作中应用这些研究成果 的手段。本书可作为从事计算机应用、人工智能、自 动控制、以及经济管理等领域研究者的学习和阅读参 考，同时高等院校相关专业研究生以及人工智能爱好 者也可从中获得借鉴。

多主体强化学习协作策略研究 目录

chapter 1introduction1.1reinforcement learning1.1.1generality of reinforcement learning1.1.2reinforcement learning on markov decision processes1.1.3integrating reinforcement learning into agent architecture1.2multiagent reinforcement learning1.2.1multiagent systems1.2.2reinforcement learning in multiagent systems1.2.3learning and coordination in multiagent systems1.3ant system for stochastic combinatorial optimization1.3.1ants forage behavior1.3.2ant colony optimization1.3.3max-min ant system1.4motivations and consequences1.5book summarybibliographychapter 2reinforcement learning and its combination with ant colony system2.1introduction2.2investigation into reinforcement learning and swarm intelligence2.2.1temporal differences learning method2.2.2active exploration and experience replay in reinforcement learning2.2.3ant colony system for traveling salesman problem2.3the q-acs multiagent learning method2.3.1the q-acs learning algorithm2.3.2some properties of the q-acs learning method2.3.3relation with ant-q learning method2.4simulations and results2.5conclusionsbibliographychapter 3multiagent learning methods based on indirect media information sharing3.1introduction3.2the multiagent learning method considering statistics features3.2.1accelerated k-certainty exploration3.2.2the t-acs learning algorithm3.3the heterogeneous agents learning3.3.1the d-acs learning algorithm3.3.2some discussions about the d-acs learning algorithm3.4comparisons with related state-of-the-arts3.5simulations and results3.5.1experimental results on hunter game3.5.2experimental results on traveling salesman problem3.6conclusionsbibliographychapter 4action conversion mechanism in multiagent reinforcement learning4.1introduction4.2model-based reinforcement learning4.2.1dyna-q architecture4.2.2prioritized sweeping method4.2.3minimax search and reinforcement learning4.2.4rtp-q learning4.3the q-ac multiagent reinforcement learning4.3.1task model4.3.2converting action4.3.3multiagent cooperation methods4.3.4q-value update4.3.5the q-ac learning algorithm4.3.6using adversarial action instead o{ ~ probability exploration4.4simulations and results4.5conclusionsbibliographychapter 5multiagent learning approaches applied to vehicle routing problems5.1introduction5.2related state-of-the-arts5.2.1some heuristic algorithms5.2.2the vehicle routing problem with time windows5.3the multiagent learning applied to cvrp and vrptw5.4simulations and results5.5conclusionsbibliographychapter 6multiagent learning methods applied to multicast routing problems6.1introduction6.2multiagent q-learning applied to the network routing6.2.1investigation into q-routing6.2.2antnet investigation6.3some multicast routing in mobile ad hoc networks6.4the multiagent q-learning in the q-map multicast routing method6.4.1overview of the q-map multicast routing6.4.2join query packet, join reply packet and membership maintenance6.4.3convergence proof of q-map method6.5simulations and results6.6conclusionsbibliographychapter 7multiagent reinforcement learning for supply chain management7.1introduction7.2related issues of supply chain management7.3scm network scheme with multiagent reinforcement learning7.3.1scm with multiagent7.3.2the rl agents in scm network7.4application of the q-acs method to scm7.4.1the application model in scm7.4.2the q-acs learning applied to the scm system7.5conclusionbibliographychapter 8multiagent learning applied in supply chain ordering management8.1introduction8.2supply chain management model8.3the multiagent learning model for sc ordering management8.4simulations and results8.5conclusionsbibliography