We study online meta-learning with bandit feedback, with the goal of
imp...
Many practical settings call for the reconstruction of temporal signals ...
The field of emergent communication aims to understand the characteristi...
We present a PAC-Bayes-style generalization bound which enables the
repl...
We study meta-learning for adversarial multi-armed bandits. We consider ...
Consider a situation where a new patient arrives in the Intensive Care U...
Fully Bayesian approaches to sequential decision-making assume that prob...
The lower the distortion of an estimator, the more the distribution of i...
Q-learning (QL), a common reinforcement learning algorithm, suffers from...
Specifying a Reinforcement Learning (RL) task involves choosing a suitab...
Options have been shown to be an effective tool in reinforcement learnin...
We develop model free PAC performance guarantees for multiple concurrent...
Autoencoders are widely used for unsupervised learning and as a
regulari...
The recently proposed distributional approach to reinforcement learning
...
In representational lifelong learning an agent aims to continually learn...
The Human visual perception of the world is of a large fixed image that ...
The process of dynamic state estimation (filtering) based on point proce...
In the wake of recent advances in experimental methods in neuroscience, ...
Agents acting in the natural world aim at selecting appropriate actions ...
Significant success has been reported recently using deep neural network...