1. Mastering strategy card game (legends of code and magic) via end-to-end policy and optimistic smooth fictitious play;Xi,2023
2. Agent57: Outperforming the atari human benchmark;Badia
3. Unsupervised predictive memory in a goal-directed agent;Wayne,2018
4. Mastering the game of Go with deep neural networks and tree search
5. Dota 2 with large scale deep reinforcement learning;Berner,2019