墨门

1 前言 此博文是南溪学习《REINFORCEMENT LEARNING (DQN) TUTORIAL》的笔记~ 2 代码学习 2.1 Hyperparameters and utilities 这里主要是超参数的设置； BATCH_SIZE = 128 GAMMA = 0.999 EPS_START = 0.9 EPS_END = 0.05 EPS_DECAY = 200 TARGET_UPDATE = 10 # Get screen size so that we can initialize lay