Current planning systems often fail to represent the reasons why certain planning decisions are made. Explicit representation of this Plan Rationale is crucial for automated plan m...
Making a truly useful massively multi-agent system is difficult since the actions of the full ensemble of agents cannot be controlled by designing just one agent. It is critical ...
Social and intentional behaviours appear as two main components of the agent paradigm. Methods of conventional software engineering do not seem to be appropriate to gain a full kno...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
Fault tolerance is an important property of large-scale multiagent systems as the failure rate grows with both the number of the hosts and deployed agents, and the duration of com...