#环境: numpy:1.23.1
torch:2.3.1——py3.9_cuda12.1_cudnn8_0
gym:0.26.2
#演示:
#参考资料: https://gymnasium.farama.org/environments/box2d/lunar_lander/
https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html
https://github.com/lazavgeridis/LunarLander-v2/blob/main/README.md