A fundamental question in the theory of reinforcement learning is: suppose the optimalQ-function lies inthe linear span ofagivenddimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and remarkable result of Weisz et al. (2020) resolves this question in the negative, providinganexponential(ind)samplesizelowerbound,whichholdsevenifthe agent has access to a generative model of the environment. One may hope that such a lower can be circumvented with an even stronger assumption that there isaconstant gapbetween the optimalQ-value ofthe best action and that ofthe second-best action (for allstates); indeed, the construction inWeisz etal.

Over the last decade, the leakage of private information by machine learning and data mining algorithms has had dramatic consequences, from losses of billions of dollars [60] to even costing humanlives[8].

We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction.

Deep equilibrium models (DEQs) refrain from the traditional layer-stacking paradigm and turn tofind the fixed point ofasingle layer.

We introduce the GANformer2 model, an iterative object-oriented transformer, explored for the task of generative modeling.

Self-supervised learning on graphs aims to learn graph representations in an unsupervised manner.

Graph convolution networks (GCNs) have become effective models for graph classification.