CMWU achieves constant regret ofln(m)/η in all normal-form games with m actions and fixed step-sizesη.

This gave birth to learning-augmented algorithms, which use these predictions to go beyond the standard long-standing worst-case limitations. The design of such algorithms requires establishing good tradeoffs between consistency and robustness, i.e. having improved performance when the predictions are accurate, and not behaving poorly

However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality.

Deep reinforcement learning (RL) has achieved remarkable successes in complex tasks, e.g Go [

Computational cognitive models are a fundamental tool in behavioral neuroscience.

We study the connection between gradient-based meta-learning and convex optimisation. We observe that gradient descent with momentum is a special case of meta-gradients, and building on recent results in optimisation, we prove convergence rates for meta-learning in the single task setting.