Human intelligence heavily depends on acquiring knowledge from other humans accumulated through time as part of our cultural evolution.
But canAIalso develop social learning skills the same way?
But usually AI tools need multiple examples and exposure to vast amounts ofdatato successfully copy their trainer.
To help the AI learn, the researchers used reinforcement learning.
The AI agents understood quickly that the best way to reach their destination was to learn from the experts.
The researchers observations were twofold.
They also look forward to further interdisciplinary cooperation between the fields of AI and cultural evolutionary psychology.
Despite its early stage, DeepMinds breakthrough could have significant implications for the artificial intelligence industry.
The full study is published on the journalNature Communications.
Story byIoanna Lykiardopoulou
Ioanna is a writer at TNW.
With a background in the humanities, she has a soft spot for social impact-enabling technologies.
