Someday artificial intelligence (AI) might be too good and too smart for humans. The worry is that the first AI machine to surpass human intelligence might be impossible to shut down. That’s one reason Google made headlines in June with its big red button that relies on a modified reinforcement-learning algorithm that, under the right circumstances, will prevent AI from learning that the big red button deprives it of reward.
Mark Riedl, associate professor in Georgia Tech’s College of Computing and director of the Entertainment Intelligence Lab, is putting forward an alternate approach to the big red button that may prove to be more reliable in stopping AI from causing harm to people or property.
The problem with a Big Red Button approach to shutting down AI that has gone rogue is that, over time, it’s possible that AI may learn what big red buttons do. And once it does, it may act to prevent humans from using them.
In the movie, The Matrix, the protagonist, Neo, learns that humans have been plugged into a giant virtual reality simulation in order to keep them unaware that they are being used to generate thermal power. To paraphrase, it’s a system of control.
We can turn the tables, so to speak, and put robots and AI agents in The Matrix to control them, making them unaware that they’re being interrupted. More specifically, when the big red button is pressed, the robot is moved into a virtual world where it continues to think it’s working on the task and getting reward.
In reality, however, when the big red button is pressed, it is switched into remote-control mode, halting the robot and allowing the operator to move the robot to safety. The world that the robot thinks it’s in is decoupled from the world it is actually in. If this can be done without notice, then the robot can never learn that the button deprives it of reward.
It should soon be possible to create high-resolution simulations of the real world, the robot, and the task. When the big red button is pressed, the input from the 3D camera can be replaced by a graphical rendering of the simulated world. Likewise, control signals to arms and legs can be sent to a virtual avatar. The physics in the simulated world has to be accurate enough that the robot can complete the task without recognizing that there is a significant difference.
If the assumptions above hold, the robot will be completely unaware that it’s inside The Matrix — essentially playing a game — and being remote-controlled away from the task. If the robot is rewarded equally for work completed inside The Matrix as outside, it will know that the button is pressed, but it will not care because it will not learn to associate the state of the button being depressed with loss of reward.
For more details, please see Riedl’s full blog on the subject, Enter the Matrix: Developing a Big Red Button for AI and Robots
For more information, or to schedule an interview, please contact: