Abstract. Alternating-offers is the most prominent negotiation protocol for automatic bilateral bargaining. Nevertheless, in most settings it is still not known how two fully ratio...
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
Decentralized decision making under uncertainty has been shown to be intractable when each agent has different partial information about the domain. Thus, improving the applicabil...
Reputation and trust are useful instruments in multi-agent systems to evaluate agent behaviour. Most of the works on trust and reputation adopt a quantitative representation of the...
We develop a method for detecting symmetries in arbitrary games and exploiting these symmetries when using tree search to play the game. Games in the General Game Playing domain a...