Use of a Semantic Language to Reduce the Indeterminacy in Agents Communication

In the field of agent communications uncertainty and vagueness in the message content and in the achievable results play a primordial role when two agents (human or artificial) communicate. Even though the importance of vagueness and uncertainty has been recognized long ago, only recently mechanisms related to the communications' semantics that allow a practical approach have been designed; more specifically, the development of tools such as agent programming languages and frameworks, which is a field of intensive research. On the other hand, recent theoretical ideas, drawn from situation semantics theory and the works of Sutton on semantic information, support this work. This paper applies these ideas to the field of multi-agent systems (MAS) and sketches how one can reduce the impact of vagueness and uncertainty present in the communication between software agents by means of context information, collaboration and basic reinforcement learning using a language designed for agent communication: the Sematic Agent Programming Language (S-APL).