← 返回论文库

Playing Atari with Deep Reinforcement Learning (DQN)

Mnih, et al. (DeepMind) · 2013
L5.1 · Algorithmic FoundationsNature 518 (2015)#rl
CORE IDEA
Deep Q-Network：CNN + Q-learning，第一次 deep RL 大规模成功。
L-ANCHOR · 为什么在这一层重要
deep RL 起点
arXiv:1312.5602 ↗

相关论文

QuantFactor REINFORCE
L0.32024
DeepSeek-R1: Incentivizing Reasoning in LLMs via RL
L4.22025
Q-Learning
L5.11989
Mastering the Game of Go with Deep Neural Networks and Tree Search (AlphaGo)
L5.12016