If I had to recommend one web site on the web, it would be Quanta Magazine <https://www.quantamagazine.org/>. It's free, its articles are superb and filled with endless links to explore.
Today, starting from... An Idea From Physics Helps AI See in Higher Dimensions <https://www.quantamagazine.org/an-idea-from-physics-helps-ai-see-in-higher-dimensions-20200109/>, lead to... Clever Machines Learn How to be Curious <https://www.quantamagazine.org/clever-machines-learn-how-to-be-curious-20170919/>, lead to... This YouTube channel, <https://www.youtube.com/watch?v=aom4RMOHezc> including this video <https://www.youtube.com/watch?v=0Ey02HT_1Ho>, with links to arXiv.org. <https://arxiv.org/> Along the way I learned that the biggest challenges facing Deep Reinforcement learning is the scarcity of reward signals. One solution is curiosity, an *intrinsic* reward that is independent of the particulars of the to-be-learned environment. Imo, this has a direct connection to human accomplishment and happiness. Edward -- You received this message because you are subscribed to the Google Groups "leo-editor" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/leo-editor/fae939ca-9bd4-42e2-b500-76e2a2a48f69%40googlegroups.com.
