yistLin / lunar-lander

Lunar Lander

Train an agent using Vanilla Policy Gradient to play LunarLander-v2 in OpenAI Gym.

Setup

pip install -r requirements.txt

Usage

To train an agent:

python train_agent.py <PATH_TO_SAVE_CHECKPOINT>

To watch a play by the trained agent:

python watch_play.py <PATH_TO_SAVED_CHECKPOINT>