MIT presents AI frameworks that compress models and encourage agents to explore

In a pair of papers accepted to the International Conference on Learning Representations (ICLR) 2020, MIT researchers investigated new ways to motivate software agents to explore their environment and pruning algorithms to make AI apps run faster. Taken together, the twin approaches could foster the development of autonomous industrial, commercial, and home machines that require less computation but are simultaneously more capable than products currently in the wild. One team created a meta-learning algorithm that generated 52,000 exploration algorithms, or algorithms that drive agents to widely explore their surroundings. Two they identified were entirely new and resulted in exploration that improved learning in a range of simulated tasks -- from landing a moon rover and raising a robotic arm to moving an ant-like robot. The team's meta-learning system began by choosing a set of high-level operations (e.g., basic programs, machine learning models, etc.) to guide an agent to perform various tasks, like remembering previous inputs, comparing and contrasting current and past inputs, and using learning methods to change its own modules.