Recent advancements in meta-learning have enabled the automatic discovery of novel
reinforcement learning algorithms parameterized by surrogate objective functions. To …

While reinforcement learning (RL) holds great potential for decision making in the real world,
it suffers from a number of unique difficulties which often need specific consideration. In …

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers
have achieved remarkable success in supervised learning, outperforming classical hand …

Deep reinforcement learning (RL) provides powerful methods for training optimal sequential
decision-making agents. As collecting real-world interactions can entail additional costs and …

While large models trained with self-supervised learning on offline datasets have shown
remarkable capabilities in text and image domains, achieving the same generalisation for …

Despite the successes and progress of deep reinforcement learning over the last decade,
several challenges remain that hinder its broader application. Some fundamental aspects to …

Open-endedness stands to benefit from the ability to generate an infinite variety of diverse,
challenging environments. One particularly interesting type of challenge is meta-learning (" …

Reinforcement learning is a machine learning paradigm that allows learning through
interaction. It intertwines data collection and model training into a single problem statement …

Due to their simplicity and support of high levels of parallelism, evolutionary algorithms have
regained popularity in machine learning applications such as curriculum generation for …