In a preprint paper, researchers at Alphabets DeepMind and the University of California, Berkeley propose a framework for comparing the ways children and AI learn about the world. The work, which was motivated by research suggesting childrens learning supports behaviors later in life, could help close the gap between AI and humans when it comes to acquiring new abilities. For instance, it might lead to robots that can pick and pack millions of different kinds of products while avoiding various obstacles.

Exploration is a key feature of human behavior, and recent evidence suggests children explore their surroundings more often than adults. This is thought to translate to more learning that enables powerful, abstract task generalization a type of generalization AI agents could tangibly benefit from. For instance, in one study, preschoolers who played with a toy developed a theory about how the toy functioned, such as determining whether its blocks worked based on their color, and they used this theory to make inferences about a new toy or block they hadnt seen before. AI can approximate this kind of domain and task adaptation, but it struggles without a degree of human oversight and intervention.

The DeepMind approach incorporates an experimental setup built atop DeepMind Lab, DeepMinds Quake-based learning environment comprising navigation and puzzle-solving tasks for learning agents. The tasks require physical or spatial navigation skills and are modeled after games children play. In the setup, children are allowed to interact with DeepMind Lab through a custom Arduino-based controller, which exposes the same four actions agents would use: move forward, move back, move left, and turn right.

During experiments approved by UC Berkeleys institutional review board, the researchers attempted to determine two things:

In one test, children were told to complete two mazes one after another each with the same layout. They explored freely in the first maze, but in the second they were told to look for a gummy.

The researchers say that in the no-goal condition the first maze the childrens strategies closely resembled that of a depth-first search (DFS) AI agent, which pursues an unexplored path until it reaches a dead-end and then turns around to explore the last path it saw. The children made choices consistent with DFS 89.61% of the time compared to the goal condition (the second maze), in which they made choices consistent with DFS 96.04% of the time. Moreover, children who explored less than their peers took the longest to reach the goal (95 steps on average), while those who explored more found the gummy in the least amount of time (66 steps).

The team notes that these behaviors are in contrast with the techniques used to train AI agents, which often depend on having the agent stumble upon an interesting area by chance and then encouraging it to revisit that area until it is no longer interesting. Unlike humans, which are prospective explorers, AI agents are retrospective.

In another test, children aged four to six were told to complete two mazes in three phases. In the first phase, they explored the maze in a no-goal condition, a sparse condition with a goal and no immediate rewards, and a dense condition with both a goal and rewards leading up to it. In the second phase, the children were tasked with once again finding the goal item, which was in the same location as during exploration. In the final phase, they were asked to find the goal item but with the optimal route to it blocked.

Initial data suggests that children are less likely to explore an area in the dense rewards condition, according to the researchers. However, the lack of exploration doesnt hurt childrens performance in the final phase. This isnt true of AI agents typically, dense rewards make agents less incentivized to explore and lead to poor generalization.

Our proposed paradigm [allows] us to identify the areas where agents and children already act similarly and those in which they do not, concluded the coauthors. This work only begins to touch on a number of deep questions regarding how children and agents explore In asking [new] questions, we will be able to acquire a deeper understanding of the way that children and agents explore novel environments, and how to close the gap between them.

More here:

DeepMind compares the way children and AI explore - VentureBeat