Recent multi-agent extensions of Q-Learning require knowledge of other agents’ payoffs and Q-functions, and assume game-theoretic play at all times by all other agents. This pap...
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...
Cooperative multi-agent systems are ones in which several agents attempt, through their interaction, to jointly solve tasks or to maximize utility. Due to the interactions among t...
This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value ...
Engineering individual components of a multi-agent system and their interactions is a complex and error-prone task in urgent need of methods and tools. Prototyping is a valuable t...
Wamberto Weber Vasconcelos, Carles Sierra, Marc Es...