§ feed · storyline
Emergent tool use from multi-agent interaction
OpenAI reports hide-and-seek agents spontaneously developing six distinct tool-use strategies through multi-agent reinforcement learning in a simulated environment.
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.
§ sources1 publication · timeline below