How AI Juggles Conflicing Goals: The Video Game of Life

Tuesday - July 11 2023, 22:41 UTC - 1 year ago

In a study led by Dr. Jonathan Cohen at the Princeton Neuroscience Institute, a modular agent composed of two sub-networks was built. The AI outperformed its classic monolithic peer, and when the researchers artificially increased the number of goals that it had to simultaneously maintain, the AI adapted rapidly. This sheds light on both human nature and AI agents as it relates to battling conflicting goals.

Every day we’re juggling different needs. I’m hungry but exhausted; should I collapse on the couch or make dinner? I’m overheating in dangerous temperatures but also extremely thirsty; should I chug the tepid water that’s been heating under the sun, or stick my head in the freezer until I have the mental capacity to make ice? When faced with dilemmas, we often follow our basic instincts without a thought. But under the hood, multiple neural networks are competing to make the "best" decision at any moment. Sleep over food. Freezer over lukewarm water. They may be terrible decisions in hindsight—but next time around, we learn from our past mistakes. Our adaptability to an ever-changing world is a superpower that currently escapes most AI agents. Even the most sophisticated AI agents break down—or require untenable amounts of computing time—as they juggle conflicting goals.

To a team led by Dr. Jonathan Cohen at the Princeton Neuroscience Institute, the reason is simple: machine learning systems generally act as a single entity, forced to evaluate, calculate, and execute one goal at a time. Although able to learn from its mistakes, the AI struggles to find the right balance when challenged with multiple opposing goals simultaneously. So why not break the AI apart? .

In a new study published in PNAS, the team took a page from cognitive neuroscience and built a modular AI agent. The idea is seemingly simple. Rather than a monolithic AI—a single network that encompasses the entire "self"—the team constructed a modular agent, each part with its own "motivation" and goals but commanding a single "body." Like a democratic society, the AI system argues within itself to decide on the best response, where the action most likely to yield the largest winning outcome guides its next step.

In several simulations, the modular AI outperformed its classic monolithic peer. Its adaptability especially shined when the researchers artificially increased the number of goals that it had to simultaneously maintain. The Lego-esque AI rapidly adapted, whereas its monolithic counterpart struggled to catch up.

"One of the most fundamental questions about agency is how an individual manages conflicting needs," said the team. By deconstructing an AI agent, the research doesn’t just provide insight into smarter machine learning agents. It also "paves the way to understanding psychological conflicts inherent in the human psyche," wrote Dr. Rober Boshra at Princeton University, who was not involved in the work.

How do intelligent beings learn to balance conflicting needs in a complex, changing world? The philosophical question has haunted multiple fields—neuroscience, psychology, economics—that delve into human nature. We don’t yet have clear answers. But with AI increasingly facing similar challenges as it enters the real world, it’s time to tackle the age-old problem head-on.

The new study took up the challenge in the form of a simple RPG (role-playing game). There are two characters that navigate a grid-like world, each trying to find resources to survive.

The first contestant: the monolithic agent—otherwise known as the "One AI Architect" character—acts as one. In a single network, the AI juggles rewards, penalties, and obstacles as it navigates the grid.

The second contestant: the modular agent—built with two sub-networks—acts like a two-player game. Each sub-network controls a specific area: seeking rewards, avoiding obstacles, and so on.

The result? The composite AI agent outperformed its monolithic counterpart. After a few hundred "episodes," or games, the bicameral AI achieved a greater reward overall, completing its struggles faster and with fewer mistakes.