"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"
"The system also uses reinforcement learning, where each action is associated with either a positive or negative response. The agents then learn through trial and error. In all, the process was trained using more than 800 million frames of the game."
"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."
"AI that cuts its teeth on Ms. Pac-Man could go on to make complex decisions in business environments – such as coming up with call lists for sales executives by prioritizing clients based on known information about their histories and schedules – that end up saving human resources valuable time."
"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."
"Ms. Pac-Man proved an excellent testing ground, given the complexity of the game. With ghosts and fruit moving in unpredictable ways, the team set up a reward system for the 150+ AI agents for recommending good moves to the “CEO,” and giving individual responsibility to the agents."
"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."
"Instead of having one algorithm learn one complex problem, [Maluuba's] AI distributes learning over many smaller algorithms, each tackling simpler problems. This research could be applied to other highly complex problems, like financial trading, according to the company."
"The technology would also help people who need to search through a very large amount of information find that one specific piece of data they need. For instance, it could help people more quickly find information hidden in car manuals or tax regulations."
"With Maluuba, Microsoft is going beyond the concepts of image recognition and machine learning to make artificial intelligence smarter, and building systems that can read text, comprehend the context behind it and even ask and answer questions."
"Maluuba wants to solve the problem of text understanding, building machines that can read and write. It’s building machines that can reason with text and effectively communicate with people."
"Microsoft is buying Maluuba, a Canadian startup focused on giving software a better understanding of human language. This natural language processing technology is a key underpinning of artificial intelligence."