This repository implements a DDPG agent with parametric noise for exploration and prioritized experience replay buffer to train the agent faster and better for the openai-gym's "LunarLanderContinuous-v2".
Let's see how fast and better it is!
-
DDPG + PNE + PER
-
Vanilla DDPG (I like Vanilla that is why! :>)
Install dependencies using this,
pip install -r requirements.txt - Add adaptive parametric noise for exploration
- Name: Kanishk Navale
- Email: navalekanishk@gmail.com
- Website: https://kanishknavale.github.io/