← 返回论文库

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (MuZero)

Schrittwieser, et al. (DeepMind) · 2019
L5.1 · Algorithmic FoundationsNature 588 (2020)#rl#model-based
CORE IDEA
不需要知道 game rules：learned world model + MCTS planning。
L-ANCHOR · 为什么在这一层重要
model-based RL 顶点
arXiv:1911.08265 ↗

相关论文

QuantFactor REINFORCE
L0.32024
DeepSeek-R1: Incentivizing Reasoning in LLMs via RL
L4.22025
Q-Learning
L5.11989
Playing Atari with Deep Reinforcement Learning (DQN)
L5.12013