Agents That Imagine And Plan


An Article from DeepMind

"Imagining the consequences of your actions before you take them is a powerful tool of human cognition. When placing a glass on the edge of a table, for example, we will likely pause to consider how stable it is and whether it might fall. On the basis of that imagined consequence we might readjust the glass to prevent it from falling and breaking. This form of deliberative reasoning is essentially ‘imagination’, it is a distinctly human ability and is a crucial tool in our everyday lives.

In two new papers, Google's Deepmind describe a new family of approaches for imagination-based planning. They also introduce architectures which provide new ways for agents to learn and construct plans to maximise the efficiency of a task. These architectures are efficient, robust to complex and imperfect models, and can adopt flexible strategies for exploiting their imagination.

The agents they introduce benefit from an ‘imagination encoder’- a neural network which learns to extract any information useful for the agent’s future decisions, but ignore that which is not relevant."

To continue reading, click here