A deep reinforcement learning algorithm can solve the Rubik’s Cube puzzle in a fraction of a second. The work is a step toward making AI systems that can think, reason, plan and make decisions.
The learning algorithm called DeepCubeA was programmed by UCI computer scientists and mathematicians. In the fraction of a second, the AI goes through billions of potential paths with the primary goal of displaying a solid color on each of the six sides of the cube. It solved 100 percent of all tests, finding the shortest path to the goal about 60 percent of the time.
Senior author Pierre Baldi, UCI Professor of computer science stated, “Artificial intelligence can defeat the world’s best human chess and Go players, but some of the more difficult puzzles, such as the Rubik’s Cube, had not been solved by computers, so we thought they were open for AI approaches. The solution to the Rubik’s Cube involves more symbolic, mathematical and abstract thinking, so a deep learning machine that can crack such a puzzle is getting closer to becoming a system that can think, reason, plan and make decisions.”
The AI learned how to solve the cube on its own, while also trying to complete the cube in less than 20 moves every time. The ultimate goal of this project is to build the next generation of AI systems and it seems like they are one step closer to reaching that goal.
For more information, check out these posts:
- Artificial Intelligence Can Diagnose PTSD By Analyzing Voices
- Artificial Intelligence Is Learning How To Outsmart Hackers
- Companies Are Spending Over $5 Million On Artificial Intelligence
- Enhance Customer Experience with Artificial Intelligence and Robotics
- Quantum Artificial Life Created On The IBM Cloud Quantum Computer
- Quarantine Cyber Attackers With Artificial Intelligence
- Digital Transformation 2019