Learning to Perform Physics Experiments via Deep Reinforcement Learning
This work addresses the challenge of developing AI with scientific intuition akin to humans, though it is incremental as it builds on existing deep reinforcement learning methods in a new task domain.
The paper tackled the problem of enabling AI agents to infer physical properties like mass and friction by interacting with objects in a simulated environment, and found that deep reinforcement learning methods can learn to perform experiments to discover these hidden properties, with strategies varying based on problem difficulty and cost trade-offs.
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances in artificial intelligence have yielded machines that can achieve superhuman performance in Go, Atari, natural language processing, and complex control problems; however, it is not clear that these systems can rival the scientific intuition of even a young child. In this work we introduce a basic set of tasks that require agents to estimate properties such as mass and cohesion of objects in an interactive simulated environment where they can manipulate the objects and observe the consequences. We found that state of art deep reinforcement learning methods can learn to perform the experiments necessary to discover such hidden properties. By systematically manipulating the problem difficulty and the cost incurred by the agent for performing experiments, we found that agents learn different strategies that balance the cost of gathering information against the cost of making mistakes in different situations.