Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …

Context is widely regarded as a major determinant of learning and memory across
numerous domains, including classical and instrumental conditioning, episodic memory …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

We demonstrate that models trained only in simulation can be used to solve a manipulation
problem of unprecedented complexity on a real robot. This is made possible by two key …

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more
quickly, by leveraging prior experience to learn how to learn. However, much of the current …

The fundamental mathematical tools needed to understand machine learning include linear
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …

Although reinforcement learning methods can achieve impressive results in simulation, the
real world presents two major challenges: generating samples is exceedingly expensive …

We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-
overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model …

Deep reinforcement learning (DRL) augments the reinforcement learning framework, which
learns a sequence of actions that maximizes the expected reward, with the representative …

Trading off exploration and exploitation in an unknown environment is key to maximising
expected return during learning. A Bayes-optimal policy, which does so optimally, conditions …