2022 Paper Urges New AI Exploration Approaches
Minqi Jiang submitted the November 2022 arXiv paper General Intelligence Requires Rethinking Exploration with two co-authors. The work argues that progress toward general intelligence requires moving beyond reinforcement learning to new methods for agents to explore and select data. It frames an emerging shift from learning from data to learning what data to learn from. The paper resurfaced on X as relevant to self-teaching systems, with co-author Edward Grefenstette crediting Jiang for the central ideas.
Nice of @jennyzhangzt to share this paper, which I selfishly think was ahead of its time. The context was that I was leaving Meta to do another startup, and thought I would not be writing papers for years. Of course, @MinqiJiang had all the good ideas + did most of the writing 😅
was reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching
then i realized it was from 2022
was reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching then i realized it was from 2022
many such cases
was reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching then i realized it was from 2022
@egrefen @jennyzhangzt Thanks for the kind words (and for originally instigating this paper)!
Talking through and rethinking these ideas together over the ~6 months spent writing this was the most transformative part of my PhD, when I figured out to a great extent what I believed as a researcher.
Nice of @jennyzhangzt to share this paper, which I selfishly think was ahead of its time. The context was that I was leaving Meta to do another startup, and thought I would not be writing papers for years. Of course, @MinqiJiang had all the good ideas + did most of the writing 😅