From Zero to Master in Hours: AlphaZero Accelerates Reinforcement Learning

Google’s DeepMind has once again surprised the machine learning community, this time with the introduction of AlphaZero — a new algorithm that can quickly surpass human board game performance through reinforcement learning self-play. It was was just two months that DeepMind published their Nature paper on AlphaGo Zero, which mastered the game of Go in

Reinforcement Learning Reading Group – Page 3 – Reinforcement Learning Reading Group for the Parr Group and Associates

From Zero to Master in Hours: AlphaZero Accelerates Reinforcement Learning

Reinforcement Learning, Fast and Slow: Trends in Cognitive Sciences

A survey of deep reinforcement learning application in 5G and beyond network slicing and virtualization - ScienceDirect

Deep Reinforcement Learning for Digital Materials Design

Reinforcement Learning

Reinforcement learning algorithms: A brief survey - ScienceDirect

Systematic Performance Evaluation of Reinforcement Learning Algorithms Applied to Wastewater Treatment Control Optimization

Reinforcement Learning – Silverton Consulting

AlphaZero

Mastering construction heuristics with self-play deep reinforcement learning

GitHub - adepierre/Caffe_AlphaZero: Implementation of Deepmind's AlphaZero algorithm with Caffe and C++

Mastering the game of Go without human knowledge

PDF] Accelerating and Improving AlphaZero Using Population Based Training

GitHub - CogitoNTNU/AlphaZero: An implementation of AlphaZero, trained to master Tic-Tac-Toe and Four in a row