The relationship between the different value targets; AlphaZero uses

AlphaDDA: strategies for adjusting the playing strength of a fully trained AlphaZero system to a suitable human training partner [PeerJ]

Comparison of network architecture of AlphaZero and NoGoZero+ (5

Evolutionary Reinforcement Learning: A Survey

Electronics, Free Full-Text

The relationship between the different value targets; AlphaZero uses

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios – arXiv Vanity

What's Inside AlphaZero's Chess Brain?

Playing Chess With A Generalized AI, by Ben Bellerose

Playing Chess With A Generalized AI, by Ben Bellerose

The relationship between the different value targets; AlphaZero uses

A molecular optimization framework to identify promising organic radicals for aqueous redox flow batteries