← 返回论文库
Mastering the Game of Go with Deep Neural Networks and Tree Search (AlphaGo)
Silver, et al. (DeepMind) · 2016
L5.1 · Algorithmic FoundationsNature 529 (2016)#rl#mcts
CORE IDEA
Policy network + Value network + MCTS，打败 Lee Sedol。
L-ANCHOR · 为什么在这一层重要
NN + MCTS 融合