Ubisoft Uses AI To Teach a Car To Drive Itself in a Racing Game (venturebeat.com) 14
An anonymous reader shares a report: Reinforcement learning, an AI training technique that employs rewards to drive software policies toward goals, has been applied successfully to domains from industrial robotics to drug discovery. But while firms including OpenAI and Alphabet's DeepMind have investigated its efficacy in video games like Dota 2, Quake III Arena, and StarCraft 2, few to date have studied its use under constraints like those encountered in the game industry. That's presumably why Ubisoft La Forge, game developer Ubisoft's eponymous prototyping space, proposed in a recent paper an algorithm that's able to handle discrete, continuous video game actions in a "principled" and predictable way. They set it loose on a "commercial game" (likely The Crew or The Crew 2, though neither is explicitly mentioned) and report that it's competitive with state-of-the-art benchmark tasks.
"Reinforcement Learning applications in video games have recently seen massive advances coming from the research community, with agents trained to play Atari games from pixels or to be competitive with the best players in the world in complicated imperfect information games," wrote the coauthors of a paper describing the work. "These systems have comparatively seen little use within the video game industry, and we believe lack of accessibility to be a major reason behind this. Indeed, really impressive results ... are produced by large research groups with computational resources well beyond what is typically available within video game studios." The Ubisoft team, then, sought to devise a reinforcement learning approach that'd address common challenges in video game development. They note that data sample collection tends to be a lot slower generally, and that there exist time budget constraints over the runtime performance of agents.
"Reinforcement Learning applications in video games have recently seen massive advances coming from the research community, with agents trained to play Atari games from pixels or to be competitive with the best players in the world in complicated imperfect information games," wrote the coauthors of a paper describing the work. "These systems have comparatively seen little use within the video game industry, and we believe lack of accessibility to be a major reason behind this. Indeed, really impressive results ... are produced by large research groups with computational resources well beyond what is typically available within video game studios." The Ubisoft team, then, sought to devise a reinforcement learning approach that'd address common challenges in video game development. They note that data sample collection tends to be a lot slower generally, and that there exist time budget constraints over the runtime performance of agents.
Re: slashdot is low-quality bs recently (Score:1)
Re: slashdot is high-quality news recently (Score:1)
Re: slashdot is high-quality news recently (Score:1)
Re: (Score:2)
So that is why the moon is made of president cheese? How are we then supposed to get free baby oil?
nonsense (Score:3, Interesting)
they did not teach it to drive. it only did acceleration and braking not steering. its a complete fabrication as usual with clickbait headline.
Re: (Score:2)
And even if the car did the steering, there would be little relation to the real world where the car has to decide where it can drive rather than being told where the road is because the road was created as part of the game.
I think in the interest of improving actual real world driving technology, all accident information should be catalogued thoroughly and made publicly available.
Re: (Score:2)
it only did acceleration and braking not steering.
Huh?
We trained a vehicle in a Ubisoft game, using the proposed Hybrid SAC with two continuous actions (acceleration and steering) and one binary discrete action (hand brake).
Re: (Score:2)
teach it to drive.
it only did acceleration and braking not steering
acceleration +1/3
braking +1/3
not steering -1/3
============
2/3rds, or 66%. Round upwards and you've got 100%, so proven true. QED.
Learn by doing. (Score:2)