Emergent tool use from multi-agent interaction
Multi-agent hide-and-seek training produced six emergent strategies and counter-strategies, demonstrating that simple objectives can yield complex tool use behaviors through co-adaptation.
Excerpt
We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported. The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day produce extremely complex and intelligent behavior.
Read at source: https://openai.com/index/emergent-tool-use