Yutian Chen

TL;DR: An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.

TL;DR: Gato as mentioned in this paper is a generalist agent that can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens.

TL;DR: It is shown that recurrent neural network optimizers trained on simple synthetic functions by gradient descent exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-parameter tuning tasks.

TL;DR: In this paper, an approximate MH rule based on a sequential hypothesis test was proposed to accept or reject samples with high confidence using only a fraction of the data required for the exact MH rule.

TL;DR: The kernel herding algorithm as mentioned in this paper is an infinite memory deterministic process that learns to approximate a PDF with a collection of samples, and it has been shown that it decreases the error of expectations of functions in the Hilbert space at a rate O(1/T) which is much faster than the usual O(T) for iid random samples.