Skip to content

An Improved Deep Q-learning algorithm for learning in environments with sparse rewards through model-based guided exploration

Notifications You must be signed in to change notification settings

stephengou/Deep-Q-Learning-with-Model-Based-Exploration

Repository files navigation

DQN with Model-Based Exploration

We proposed Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. Detail can be found in the paper: DQN with Model-based exploration.pdf.

Run the code:

  • Make sure to have installed necessary packages in your python environment.
  • run train_model.py to train.

About

An Improved Deep Q-learning algorithm for learning in environments with sparse rewards through model-based guided exploration

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published