Computer Sciences

New 'bandit' algorithm uses light for better bets

How does a gambler maximize winnings from a row of slot machines? This is the inspiration for the "multi-armed bandit problem," a common task in reinforcement learning in which "agents" make choices to earn rewards. Recently, ...

Energy & Green Tech

Improving EV batteries with real-world driving data

Most electric vehicles are equipped with an electronic brain that manages day-to-day battery performance and safety. This battery management system, or BMS, includes software that uses algorithms to monitor the overall health ...

Computer Sciences

Evolutionary computation for expensive optimization: A survey

The term 'Expensive optimization problem' (EOP) refers to any problem that requires expensive or even unaffordable costs to evaluate candidate solutions. These problems exist in many significant real-world applications.

page 14 from 40