Online learning represents a family of machine learning methods, where a learner attempts
to tackle some predictive (or any type of decision-making) task by learning from a sequence …

This chapter studies the bidirectional causal interactions between curiosity and learning and
discusses how understanding these interactions can be leveraged in educational …

In this paper, we make the key delineation on the roles of resolution and statistical
uncertainty in hierarchical bandits-based black-box optimization algorithms, guiding a more …

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a
previously collected static dataset, bears algorithmic difficulties due to function …

We study reinforcement learning (RL) with linear function approximation where the
underlying transition probability kernel of the Markov decision process (MDP) is a linear …

Off-policy deep reinforcement learning (RL) has been successful in a range of challenging
domains. However, standard off-policy RL algorithms can suffer from several issues, such as …

Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

Grey-box fuzzing is a practically effective approach to test real-world programs. However,
most existing grey-box fuzzers lack directedness, ie the capability of executing towards user …

Time-uniform, nonparametric, nonasymptotic confidence sequences Page 1 The Annals of
Statistics 2021, Vol. 49, No. 2, 1055–1080 https://doi.org/10.1214/20-AOS1991 © Institute of …