A team of researchers in the UK has used a "reinforcement learning" algorithm alongside a human safety driver to teach the artificial intelligence.
The team at Wayve - which was founded by researchers from Cambridge University's Engineering Department - has outlined its work in a recent blog post.
It wrote: "Today's self-driving cars are stuck at good but not good enough performance levels. Here, we have provided evidence for the first viable framework to quickly improving driving algorithms from being mediocre to being roadworthy.
"The ability to quickly learn to solve tasks through clever trial and error is what has made humans incredibly versatile machines capable of evolution and survival.
"We learn through a mixture of imitation, and lots of trial and error for everything from riding a bicycle, to learning how to cook."
Wayve uploaded a video demonstrating their achievements, and it shows how the AI is "rewarded" for distance travelled without any intervention.
Differing from other self-driving cars, the modified Renault doesn't require "massive models, fancy sensors and endless data" but instead capitilises on the company's goal to use "a clever training process that learns rapidly and efficiently".