How computers can learn better

Researchers from MIT’s Laboratory for Information and Decision Systems (LIDS) and Computer Science and Artificial Intelligence Laboratory have  developed a new reinforcement-learning algorithm that allows computer systems to find solutions much more efficiently than previous algorithms did and for a wide range of problems.
With a recently released programming framework, the researchers show that a new machine-learning algorithm outperforms its predecessors.
Reinforcement learning is a technique, common in computer science, in which a computer system learns how best to solve some problem through trial-and-error. Classic applications of reinforcement learning involve problems as diverse as robot navigation, network administration, and automated surveillance.
At the Association for Uncertainty in Artificial Intelligence’s annual conference this summer, the researchers will present a paper on the first application of the new programming framework.
Alborz Geramifard, a LIDS postdoc and first author of the new paper, hopes that the software, dubbed RLPy (for reinforcement learning and Python, the programming language it uses), will allow researchers to more efficiently test new algorithms and compare algorithms’ performance on different tasks. It could also be a useful tool for teaching computer-science students about the principles of reinforcement learning.
Geramifard developed RLPy with Robert Klein, a master’s student in MIT’s Department of Aeronautics and Astronautics. RLPy and its source code were both released online in April.