EAQR: A Multiagent Q-Learning Algorithm for Coordination of Multiple Agents
نویسندگان
چکیده
منابع مشابه
Multiagent Coordination in Cooperative Q-learning Systems
Many reinforcement learning architectures fail to learn optimal group behaviors in the multiagent domain. Although these coordination difficulties are often attributed to the non-Markovian environment created by the gradually-changing policies of concurrently learning agents, a careful analysis of the situation reveals an underlying problem structure which can cause suboptimal group policies ev...
متن کاملMultiagent Q-Learning by Context-Specific Coordination Graphs
One of the main problems in cooperative multiagent learning is that the joint action space is exponential in the number of agents. In this paper, we investigate a sparse representation of the joint action space in which value rules specify the coordination dependencies between the different agents for a particular state. Each value rule has an associated payoff which is part of the global Q-fun...
متن کاملApprentissage de la coordination multiagent : Q-learning par jeu adaptatif
Résumé : Dans le cadre de l’apprentissage multiagent, de nombreux travaux ont cherché jusqu’à présent à établir des algorithmes convergents vers un équilibre de Nash en jeux stochastiques. De tels algorithmes sont cependant limités dans la mesure où ils sont incapables de gérer la multiplicité des équilibres de Nash et de converger vers l’équilibre Pareto-optimal si celui-ci existe. Ces algorit...
متن کاملMultiagent coordination for Multiple Resource Job Scheduling
Efficient management of large-scale job processing systems is a challenging problem, particularly in the presence of multiusers and dynamically changing system conditions. In addition, many real world systems require the processing of multi-resource jobs where centralized coordination may be difficult. Most conventional algorithms, such as load balancing, are designed for centralized, single re...
متن کاملSparse Tabular Multiagent Q-learning
Multiagent learning problems can in principle be solved by treating the joint actions of the agents as single actions and applying singleagent Q-learning. However, the number of joint actions is exponential in the number of agents, rendering this approach infeasible for most problems. In this paper we investigate a sparse representation of the Q-function by only considering the joint actions in...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Complexity
سال: 2018
ISSN: 1076-2787,1099-0526
DOI: 10.1155/2018/7172614