Abstract: With the development of intelligent vehicles, the importance of imitating, learning, and optimizing human driving strategies is increasingly recognized. Offline reinforcement learning offers ...

Quantum computation has the potential for exponential speedup of classical systems in some applications, such as cryptography, simulation of molecular behavior, and optimization. Nevertheless, quantum ...

Abstract: We introduce a new convolutional autoencoder architecture for user modeling and recommendation tasks with several improvements over the state of the art. First, our model has the flexibility ...

This paper examines the choice of architecture for a new sequence modelling task. Traditionally, sequence modelling is synonymous with recurrent networks. However, recent results indicate that ...