DeepMind’s AlphaDev Leverages Deep Reinforcement Learning to Discover Faster Sorting Algorithms

In a new paper Faster sorting algorithms discovered using deep reinforcement learning, a DeepMind research team introduces AlphaDev, a deep reinforcement learning agent which is capable to automatically discover correct and efficient sorting algorithms that achieves superior performance then previously known human benchmarks.

ai algorithms alphadev artificial intelligence benchmarks deepmind deepmind research deep-neural-networks deep & reinforcement learning faster human machine learning machine learning & data science ml paper performance reinforcement reinforcement learning research research team sorting sorting algorithm team technology