Some resources for thinking about Universal Intelligence. Selective rather than exhaustive, biased to my taste, roughly ordered. Works dense with ideas highlighted. Resisted adding a Schmidhuber section.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Relational Inductive Biases, Deep Learning, and Graph Networks
Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
RL^{2}: Fast Reinforcement Learning via Slow Reinforcement Learning
Learning to Learn Without Gradient Descent by Gradient Descent
SMCGP2: Self Modifying Cartesian Genetic Programming in Two Dimensions
Backpropamine: Training Self-Modifying Neural Networks with Differentiable Neuromodulated Plasticity
Open-Endedness: The Last Grand Challenge You’ve Never Heard of
Minimal Criterion Coevolution: A New Approach to Open-Ended Search
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
Gödel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
A Theory of Universal Artificial Intelligence based on Algorithmic Complexity
Computable Variants of AIXI which are More Powerful than AIXItl
Quantifying the Rise and Fall of Complexity in Closed Systems: The Coffee Automaton
Computational Complexity as an Ultimate Constraint on Evolution
Top-Down Causation and Emergence: Some Comments on Mechanisms