Moreover, our algorithm is complementary to existing continual learning strategies, such as MER and GEM.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

India plans AI'data city' on staggering scale Information technology minister for India's Andhra Pradesh state, Nara Lokesh, speaks during an interview in New Delhi in January. New Delhi - As India races to narrow the artificial intelligence gap with the United States and China, it is planning a vast new data city to power digital growth on a staggering scale, the man spearheading the project says. The AI revolution is here, no second thoughts about it, said Nara Lokesh, information technology minister for Andhra Pradesh state, which is positioning the city of Visakhapatnam as a cornerstone of India's AI push. And as a nation ... we have taken a stand that we've got to embrace it, he said ahead of an international AI summit this week in New Delhi. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

There has been tremendous recent progress on equilibrium-finding algorithms for zero-sum imperfect-information extensive-form games, but there has been a puzzling gap between theory and practice. First-order methods have significantly better theoretical convergence rates than any counterfactual-regret minimization (CFR) variant. Despite this, CFR variants have been favored in practice. Experiments with first-order methods have only been conducted on small-and medium-sized games because those methods are complicated to implement in this setting, and because CFR variants have been enhanced extensively for over a decade they perform well in practice. In this paper we show that a particular first-order method, a state-ofthe-art variant of the excessive gap technique--instantiated with the dilated entropy distance function--can efficiently solve large real-world problems competitively with CFR and its variants. We show this on large endgames encountered by the Libratus poker AI, which recently beat top human poker specialist professionals at no-limit Texas hold'em. We show experimental results on our variant of the excessive gap technique as well as a prior version. We introduce a numerically friendly implementation of the smoothed best response computation associated with first-order methods for extensive-form game solving.