Reinforcement Learning

Reinforcement learning is a part of machine learning in which an agent interacts with the environment over time, and learns an optimal policy, by trial and error, for sequential decision-making problems. It has been making steady progress, with decades of research and development with the latest breakthroughs such as Atari games and AlphaGo. Each of them represents a big family of problems and the underlying techniques can be applied to a large number of applications. Recent advances in RL have been made in recommendation systems. At the AI lab we would focus on real-world RL applications for business use cases.