A former Microsoft engineer is training AI to beat 1982’s Robotron: 2084, an arcade game where a lone human must overcome endless waves of robots following a cybernetic revolt.
There’s more to it than that, of course, but the scenario is dripping with irony – asking AI to devise ways of succeeding when managing with the frenzy of a Robotron session.
Former Microsoft engineer Dave Plummer – famed for Task Manager and Space Cadet pinball – had already trained an AI model to master Atari’s 1981 vector shooter, Tempest.
The next step for the retired engineer is Robotron, into which this writer pumped pocket money, only to rapidly run out of skill in the face of conflicting priorities (rescue the humans, shoot the robots, or try to do both), a brain-melting control system (two joysticks – one for direction and one for firing), and never-ending legions of enemies.
Plummer said: “We’ve already taught one machine to dominate Tempest, which is a bit like teaching a robot to fence beautifully. Robotron is different. Robotron is teaching it to box its way out of a New Orleans riot.”
Despite its age (44 in March), Robotron remains an addictive exercise in rapid decision-making and prioritization. Or as Plummer put it: “A screaming 1982 arcade cabinet trying to murder you with a hundred simultaneous bad decisions at 60 frames a second.”
“It is a brutally compressed lesson in real-time systems, human limits, and the difference between intelligence and reflex.”
Explaining the challenge facing an AI as it navigates level after level, Plummer said that while it doesn’t suffer the panic that meatbags do, “Robotron mastery is partly tactical, partly statistical, and partly an exercise in triage under uncertainty. The AI doesn’t merely need to dodge. It needs to understand what is worth dodging toward.”
“The more I’ve dug into Robotron, the more I think it is one of the purest stress tests of real-time decision-making ever smuggled into a commercial entertainment product.”
As with Tempest, Plummer has published a live training dashboard (not a secure link) for anyone interested in the progress. Also like Tempest, it is strangely hypnotic.
Plummer said: “Robotron is an old game, yes. A magnificent one. A loud one. A deeply unfair one. But it is also a laboratory. It is a place where 30 or 40-year-old design decisions about CPU cycles, linked lists, blitter modes, jump tables, and joystick ergonomics are suddenly back on the table because they still describe a live system with measurable behavior. And the moment you point an AI at it, the game starts revealing itself all over again. Not as a museum piece, but as an active adversary.”
Or as anyone who once shoveled coins into the arcade cabinet will tell you: a bit of a git. Maybe AI will have more success at fending off the rise of the machines. ®