Scientists have created an AI program which can master classic 1980s platform games.
Researchers formed a family of algorithms - known collectively as Go-Explore - which is capable of completing Atari titles like 'Pitfall', 'Freeway' and 'Montezuma's Revenge'.
These games have been tough for AI in the past, but the algorithms could have real-world implications by helping robots better navigate certain environments.
These include the likes of disasters zones or the average home, with a range of benefits.
Researchers Adrien Ecoffet, Joost Huizinga and Jeff Clune told BBC News: "Our method is indeed pretty simple and straightforward, although that is often the case with scientific breakthroughs.
"The reason our approach hadn't been considered before is that it differs strongly from the dominant approach that has historically been used for addressing these problems in the reinforcement learning community, called 'intrinsic motivation'.
"In intrinsic motivation, instead of dividing exploration into returning and exploring like we do, the agent is simply rewarded for discovering new areas."
One issue with that method is that the algorithm can "forget" about promising areas yet to be explored, but this was overcome by compiling a list of areas visited.
Discussing their work, the team added: "In addition to robotics, Go-Explore has already seen some experimental research in language learning, where an agent learns the meaning of words by exploring a text-based game, and for discovering potential failures in the behaviour of a self-driving car."
Related Video:
BANG ShowBiz Tech