With the growing importance of multiagent teamwork, tools that can help humans analyze, evaluate, and understand team behaviors are also becoming increasingly important. To this end, we are creating isaac, a team analyst agent for post hoc, offline agent-team analysis. With the growing importance of teamwork, there is now a critical need for tools to help humans analyze, evaluate, and understand team behaviors. Indeed, in multiagent domains with tens or even hundreds of agents in teams, agent interactions are often highly complex and dynamic, making it difficult for human developers to analyze agent-team behaviors. The problem is further exacerbated in environments where agents are developed by different developers, where even the intended interactions are unpredictable.
With the growing importance of multiagent team-work, tools that can help humans analyze, evaluate, and understand team behaviors are also becoming increasingly important. To this end, we are creating isaac, a team analyst agent for post hoc, offline agent-team analysis. ISAAC'S novelty stems from a key design constraint that arises in team analysis: Multiple types of models of team behavior are necessary to analyze different granularities of team events, including agent actions, interactions, and global performance. These heterogeneous team models are automatically acquired by machine learning over teams' external behavior traces, where the specific learning techniques are tailored to the particular model learned. Additionally, ISAAC uses multiple presentation techniques that can aid human understanding of the analyses. This article presents ISAAC'S general conceptual framework and its application in the RoboCup soccer domain, where ISAAC was awarded the RoboCup Scientific Challenge Award.
Today, we live in a time characterized by rapid technology transformation, and resulting social, political, and economic disruption. In its wake, few institutions have remained untouched. The results can be dislocation, upheaval, opportunity, and inequality. Change is in the air. We are living in interesting times.
In every prediction about the future of work, artificial intelligence appears pretty close to the top of technology trends for businesses to prepare for. Google and other technology giants are developing algorithms which can learn from human inputs, meaning that they can accelerate their learning in a particular area at an incredibly rapid rate. However, before diving into a new artificial intelligence strategy for business, it's worth taking a look at what the capabilities of AI actually are right now, because the media presents a confusing picture. The first type of AI is highly achievable, and probably shouldn't be called AI at all – it's just a good algorithm. More successful types of this AI are the'recommendation engines' – characterised by you-watched-this-movie so you-may-like-this-TV-show.