"Maluuba reached its historic high score by breaking up the problem. Instead of having one agent use reinforcement learning to try and digest all the game’s complexity into a single strategy, researchers created a crowd of more than 150 learning agents"
"Researchers with deep learning company Maluuba, which Microsoft acquired earlier this year, decided to tackle the deceptively simple arcade game after developing an unusual AI algorithm that uses a team of intelligent agents overseen by a manager agent to play Ms. Pac-Man.
"Maluuba taught the AI using what they call Hybrid Reward Architecture — a combination of reinforcement learning with a divide-and-conquer method. Individual agents were assigned piecemeal tasks — like finding a specific pellet — which worked in tandem with other agents to achieve greater goals."
"With reinforcement learning, an agent gets both positive and negative responses and learns through trial and error to maximise the positive ones. Increasingly, reinforcement learning is being seen as a way to create AI that can make more autonomous decisions and perform more complex tasks."
"Breaking up complex problems into simpler, smaller problems can make it much easier for deep learning systems to be able to handle more complex behavior. That, in turn, could be applied to lots of real-world tasks that AI could be applied to in the future."