/pytorch-LunarLander

PyTorch implementation of different Deep RL algorithms for the LunarLander-v2 environment in OpenAI Gym

Primary LanguagePython

pytorch-LunarLander

PyTorch implementation of different Deep RL algorithms for the LunarLander-v2 environment in OpenAI Gym

We implemented 3 different RL algortihms to solve the LunarLander-v2 environment:

  1. Imitation Learning
  2. REINFORCE
  3. Advantage-Actor-Critic (A2C)

Note: Imitation Learning is implemented in Keras and the other two algorithms in PyTorch

Instructions:

  1. Install all the dependencies

  2. Clone the repo

  3. Run the below commands:

    3.1) python imitation.py 3.2) python reinforce.py 3.3) python a2c.py