pire mard


AI research and development company DeepMind is now looking at human psychology concepts to develop a new approach to reinforcement learning, particularly the theory of affordance.

The theory of affordance states that when intelligent beings look at the world they perceive not simply objects and their relationships, but also their possibilities.

“In other words, the chair “affords” the possibility of sitting. The water “affords” the possibility of swimming. The theory could explain in part why animal intelligence is so generalizable—we often immediately know how to engage with new objects because we recognize their affordances,” MIT Technology Review explained.

The researchers published a whitepaper explaining that reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible.

“The idea is if the robot were instead first taught its environment’s affordances, it would immediately eliminate a significant fraction of the failed trials it would have to perform. This would make its learning process more efficient and help it generalize across different environments”.

In the experiment, the researchers placed a virtual agent in a 2D environment with a wall in the middle, and had the agent explore its range of motion until it had learned what the environment would allow it to do—its affordances.

 The researchers then gave the agent a set of simple objectives to achieve through reinforcement learning, such as moving a certain amount to the right or to the left.

They found that, compared with an agent that hadn’t learned the affordances, it avoided any moves that would cause it to get blocked by the wall partway through its motion, setting it up to achieve its goal more efficiently, the MIT Tech Review wrote.

While still at the early stages, DeepMind researchers are hoping that the first experiment may lay a theoretical foundation for scaling the idea up to much more complex actions in the future.


What can I do here? A Theory of Affordances in Reinforcement Learning

You might also like

Leave A Reply

Your email address will not be published.