Applying neural networks to generate robust agent controllers is now a seasoned practice, with time needed only to isolate particulars of domain and execution. However we are often constrained to local problems due to an agents inability to reason in an abstract manner. While there are suitable approaches for abstract reasoning and search, there is often the issues that arise in using offline processes in real-time situations. In this paper we explore the feasibility of creating a decentralised architecture that combines these approaches. The approach in this paper explores utilising a classical automated planner that interfaces with a library of neural network actuators through the use of a Prolog rule base. We explore the validity of solving a variety of goals with and without additional hostile entities as well as added uncertainty in the world. The end results providing a goal-driven agent that adapts to situations and reacts accordingly.
展开▼
