For my bachelor thesis I want to create more meaningful visualisations of the Deep Reinforcement Learning (DRL) Process. This repository is solely for the use of experiments within DRL.
- Deep Q Network (DQN)
- Double Deep Q Network (DDQN)
- Dueling Deep Q Network
- Deep Deterministic Policy Gradient
- A3C . . .
The basic DQN implementation is based upon the original Nature Paper from Mnih et al.. For the DDQN and the Dueling DQN I used the corresponding papers from van Hasselt et al. and Wang et al.. Further references used for the code, are stated within the comments.
- OpenAI Gym
- Tensorflow (Keras)
- OpenCV