• Experiment Description
Programming language: python3
You should compare the performance of DQN and one kind of improved DQN and test them in a classical RL control environment{MountainCar. OPENAI gym provides this environment, which is implemented with python (https://gym.openai.com/envs/MountainCar-v0/). What’s more, gym also provides other more complex environment like atari games and mujoco.
2
©2015 Macmillan Publishers Limited. All rights reserved
Since the state is abstracted into car’s position, convolutional layer is not necessary in our experiment. You can get started with OPENAI gym refer to this link (https://gym.openai.com/docs/). Note that it is suggested to implement your neural network on the Tensor ow or Pytorch.
• Report and Submission
Your report and source code should be compressed and named after \stu-dentID+name+assignment4".
The les should be submitted on Canvas before May 15, 2020.
3
