When AI Plans Ahead

Recent advances in neural networks have generated considerable excitement about AI. But AI is not all about neural networks. Other avenues in AI research tackle problems such as building effective models of the world or logical reasoning and are especially useful for dealing with the limitations of neural networks. In this post, we examine one specific problem in AI: planning. One simple definition is that planning is an exploration to decide what actions need to be taken to achieve a given goal. The result of a planning process (i.e., the plan) is a collection of actions that would take us from the current (also known as the initial) state to a goal state. AI planning is about how to teach a machine to plan ahead.