255 citations · 2.4k across the 127 of their papers we have counts for
9 papers · 2 filters
Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks
Ilja Kuzborskij, Csaba Szepesvári
We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Desce…
Confident Approximate Policy Iteration for Efficient Local Planning in -realizable MDPs
Gellért Weisz, András György, Tadashi Kozuno +1
We consider approximate dynamic programming in -discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first con…
Revisiting Simple Regret: Fast Rates for Returning a Good Arm
Yao Zhao, Connor James Stephens, Csaba Szepesvári +1
Simple regret is a natural and parameter-free performance criterion for pure exploration in multi-armed bandits yet is less popular than the probability of missing the best arm or…
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
Hui Yuan, Chengzhuo Ni, Huazheng Wang +4
Directed Evolution (DE), a landmark wet-lab method originated in 1960s, enables discovery of novel protein designs via evolving a population of candidate sequences. Recent advances…
Near-Optimal Sample Complexity Bounds for Constrained MDPs
Sharan Vaswani, Lin F. Yang, Csaba Szepesvári
In contrast to the advances in characterizing the sample complexity for solving Markov decision processes (MDPs), the optimal statistical complexity for solving constrained MDPs (C…
Sample-Efficient Reinforcement Learning of Partially Observable Markov Games
Qinghua Liu, Csaba Szepesvári, Chi Jin
This paper considers the challenging tasks of Multi-Agent Reinforcement Learning (MARL) under partial observability, where each agent only sees her own individual observations and…