Scientists at the Johns Hopkins Applied Physics Laboratory, in Laurel, hope to make research of artificial intelligence easier with the creation of Meta Arcade, a suite of arcade games that can be used as training tasks for artificial intelligence systems.
Initially developed under the Defense Advanced Research Projects Agency’s Lifelong Learning Machines program, Meta Arcade trains AI agents to quickly adapt to new and changing scenarios.

“We needed to develop a tool like Meta Arcade to study and advance our AI research,” said Bart Paulhamus, chief of APL’s Intelligent Systems Center. “By releasing it to the public, APL is accelerating the development of trusted AI for our nation’s most critical challenges. Now, AI researchers can focus their time on AI research, not tool development.”

The games in Meta Arcade are modeled on classic games, such as Pong and Breakout, which are common benchmarks in the deep reinforcement learning community. Unlike a typical game, where settings and features are fixed, a researcher can use Meta Arcade to control the sizes, speeds and colors of game entities, or even create new games.

The ease of modifying games through Meta Arcade allows researchers to focus on an algorithm’s specific capability and measure how well an AI agent can handle changes.

The core team behind Meta Arcade includes DRL Researcher Ted Staley, AI Engineer Chace Ashcraft and Researcher Ben Stoler, all from APL’s Research and Exploratory Development Department. The tool is available to the public through the development platform GitHub.