Game Theory

Mastering Stratego Through Model-Free Multiagent Reinforcement Learning

by
Mastering Stratego Through Model-Free Multiagent Reinforcement Learning

“DeepNash is an autonomous agent capable of learning Stratego from scratch to reach human expert level. Stratego is one of the few iconic board games that artificial intelligence (AI) has yet to master. This game not only has a vast game tree, but DeepNash also needs to make decisions under conditions of incomplete information. Decisions … Read more

Multi-Agent Collaborative Control and Decision-Making in Complex Dynamic Game Environments

by

Source: Human-Machine and Cognitive LaboratoryIn complex dynamic game environments, collaborative control and decision-making among multiple agents is often a highly challenging problem, involving theories and technologies from various fields such as game theory, control theory, multi-agent systems, and machine learning. The goal of multiple agents is typically to optimize collective benefits while addressing conflicts and … Read more