This is from last Wednesday's edition of the journal Nature: *"**Reinforcement learning underpins some major advances in AI. But previous programs were specialists — they could not apply knowledge in new domains from scratch [...] **An artificial intelligence (AI) system ) [Dreamer from Google] has for the first time figured out how to collect diamonds in the hugely popular video game Minecraft** — a difficult task requiring multiple steps — without being shown how to play. Its creators say the system, called Dreamer, is a step towards machines that can generalize knowledge learn in one domain to new situations, a major goal of AI <https://www.nature.com/articles/d41586-024-03905-1> [...] **Reinforcement learning underpins some major advances in AI. But previous programs were specialists — they could not apply knowledge in new domains from scratch"*
*AI masters Minecraft: DeepMind program finds diamonds without being taught* <https://www.nature.com/articles/d41586-025-01019-w> *Mastering diverse control tasks through world models* <https://www.nature.com/articles/s41586-025-08744-2> *John K Clark See what's on my new list at Extropolis <https://groups.google.com/g/extropolis>* 3s2 -- You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/d/msgid/everything-list/CAJPayv2QbH_dDughs%3DsHn4qrW1upS-YsJmE2RWC-E4PjK%2BKQWA%40mail.gmail.com.
