"The Alberta Plan for AI Research" - "Intro" from Richard Sutton

WrRan發表於2024-10-12

origin

Herein we describe our approach to artificial intelligence (AI) research, which we call the Alberta Plan. The Alberta Plan is pursued within our research groups in Alberta and by others who are like minded throughout the world. We welcome all who would join us in this pursuit.

The Alberta Plan is a long-term plan oriented toward basic understanding of computational intelligence. It is a plan for the next 5-10 years. It is not concerned with immediate applications of what we currently know how to do, but rather with filling in the gaps in our current understanding. As computational intelligence comes to be understood it will undoubtedly profoundly affect our economy, our society, and our individual lives. Although all the consequences are difficult to foresees, and every powerful technology contains the potential for abuse, we are convinced that the existence of more far-sighted and complex intelligence will overall be good for the world.

Following the Alberta Plan, we seek to understand and create long-lived computational agents that interact with a vastly more complex world and come to predict and control their sensory input signals. The agents are complex only because they interact with a complex world over a long period of time; their initial design is as simple, general, and scalable as possible. To control their input signals, the agents must take action. To adapt to change and the complexity of the world, they must continually learn. To adapt rapidly, they must plan with a learned model of the world.

The purpose of this document is twofold. One is to describe our vision for AI research and its underly intellectual commitments and priorities. The second is to describe the path along which this vision may unfold and the research problems and projects that we will pursue. What we say toward the first goal is described here in order to establish a clear record of where we come from; this part of our research strategy is expected to be relatively stable. What we say toward the second goal is much more contemporary. The voyage is uncertain; our path has gaps and uncertainties. Nevertheless, we attempt to chart the path ahead with as much specificity as possible so that we know where we are trying to go, even if in the end we go another way or arrive at a somewhat different destination.

相關文章