Abstract
AbstractThis paper explores the combination of model-based methods and multi-agent reinforcement learning (MARL) for more efficient coordination among multiple agents. A decentralized model-based MARL method, Policy Optimization with Dynamic Dependence Modeling (POD2M), is proposed to dynamically determine the importance of other agents’ information during the model building process. In POD2M, the agents adapt their mutual dependence during building their own dynamic models in order to make a trade-off between an individual-learning process and a coordinated-learning process. Once the dynamic models have been built, the policies are then trained based on one-step model predictive rollouts. Empirical experiments on both cooperative and competitive scenarios indicate that our method can achieve higher sample efficiency against the compared model-free MARL algorithms, and outperforms the centralized method in large domains.KeywordsMulti-agent reinforcement learningModel-based policy optimizationDynamic dependence
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
