Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent

TL;DR

This survey reviews meta-learning and meta-reinforcement learning, highlighting their role in developing DeepMind's Adaptive Agent by formalizing concepts and tracing key algorithmic milestones.

Contribution

It provides a rigorous task-based formalization of meta-learning and chronicles landmark algorithms leading to DeepMind's Adaptive Agent.

Findings

Formalization of meta-learning and meta-reinforcement learning paradigms

Chronology of landmark algorithms in the field

Insights into the development of DeepMind's Adaptive Agent

Abstract

Humans are highly effective at utilizing prior knowledge to adapt to novel tasks, a capability that standard machine learning models struggle to replicate due to their reliance on task-specific training. Meta-learning overcomes this limitation by allowing models to acquire transferable knowledge from various tasks, enabling rapid adaptation to new challenges with minimal data. This survey provides a rigorous, task-based formalization of meta-learning and meta-reinforcement learning and uses that paradigm to chronicle the landmark algorithms that paved the way for DeepMind's Adaptive Agent, consolidating the essential concepts needed to understand the Adaptive Agent and other generalist approaches.