OpenAI teaches AI teamwork by playing hide-and-seek
The researchers gave the agents no other instructions. Over the course of hundreds of millions of rounds of game play, the agents developed several strategies and counter-strategies. During the first phase, the hiders and seekers developed very crude avoiding and chasing strategies by moving around the space without manipulating any of the objects. But around the million-game mark, play became more sophisticated.
The hiders learned to move and lock the boxes and barricades in the environment to build forts around themselves so the seekers would never see them. Not only that, but they also developed coordination strategies, such as passing each other objects, in order to speed up the fort-building process. After another 75 million rounds, however, the seekers discovered a counter-strategy, moving the process into phase three.
By phase four, 10 million rounds later, the hiders had learned to lock the ramps in place before building their fort. Neither team could unlock an object that was locked by an opposing team.
At first, the researchers at OpenAI believed that this was the last phase of game play, but finally, at the million-game mark, two more strategies emerged. In the final phase, the hiders once again learned to lock all the ramps and boxes in place before building their fort.https://yquwokusobof.tk
This is What Happens When You Teach an AI to Play Hide and Seek «TwistedSifter
The researchers believe that these initial results demonstrate a promising new method for evolving more complex AI. Though the lab has also invested in developing novel techniques relative to other labs, it has primarily made a name for itself by dramatically scaling existing ones.
- Lust for Liberty: The Politics of Social Revolt in Medieval Europe, 1200-1425: Italy, France and Flanders.
- More TV Shows & Movies;
- Hide and Seek Teacher;
- Playing Hide and Seek!
In a way, this study reaffirms the value of testing the limits of existing technologies at scale. The team also plans to continue with this strategy. Correction: The original headlined misstated the number of games the agents played.
After around 85 million games, though, the hiders learned to take the ramp inside the fort with them before blocking the exits, so the seekers have no tool to use. It has this really interesting analogue to how humans evolved on Earth, where you had constant competition between organisms.
The agents' development didn't even stop there. They eventually learned how to exploit glitches in their environment, such as getting rid of ramps for good by shoving them through walls at a certain angle.
Yes, the agents cheated, but what does that mean for the system?
Bower said this suggests that artificial intelligence could find solutions for complex problems that we might not think of ourselves. Buyer's Guide. Log in. Sign up.
Ask Engadget: How can I improve my rural internet?
Ask Engadget: How can I improve my rural internet? Amazon Prime perks now include mobile game add-ons.
Latest in Tomorrow. Image credit: OpenAI. Sponsored Links.
- Nightlife Entertainment Venue Hide & Seek.
- Emergent Tool Use from Multi-Agent Interaction.
- Biomedical Knowledge Management: Infrastructures and Processes for E-Health Systems!
- The Political Economy of Violence against Women?
- Trade in Services in the Asia-Pacific Region (National Bureau of Economic Research East Asia Seminar on Economics).
- Hide and Seek;
As OpenAI's Bowen Baker said : "Once one team learns a new strategy, it creates this pressure for the other team to adapt. Source: OpenAI.