图像索引>> Lunar-Lander-Deep-RL>> 返回
项目作者： shangeth

项目描述 ：
Deep Q network, DDQN, Dueling DQN for Lunar Lander Environment.
高级语言： Jupyter Notebook
项目地址: git://github.com/shangeth/Lunar-Lander-Deep-RL.git
创建时间： 2019-10-16T21:40:45Z
项目社区：https://github.com/shangeth/Lunar-Lander-Deep-RL
开源协议：
下载


Lunar Lander DRL

Environment

Reinforcement Learning Approaches

  • Discrete space - Traditional RL methods like MC, TD

  • Continuous Space

    • Discritize the space

      • Grid
      • Tile Coding
      • Coarse Coding

    • Continuous Function Approximation

      • Linear Approximation
      • kernel Approximation
      • Non-Linear Approximation

Non-Linear Approximation

Deep Q Network - Paper

Double Deep Q Network - Paper

Prioritized Experience Replay - Paper

Dueling Deep Q Network - Paper