pretidav / Reinforcement_Learning Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

3D maze dynamic environment optimization with Dyna-Q and Dyna-Q+ algorithms.

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
results		results
3D_maze.ipynb		3D_maze.ipynb
README.md		README.md
agent.py		agent.py
environment.py		environment.py
maze_env.py		maze_env.py
rl_glue.py		rl_glue.py

Repository files navigation

Reinforcement_Learning

Comparison of the well known tabular dyna-Q and dyna-Q+ algorithms in a 3d Maze dynamic environment

About

3D maze dynamic environment optimization with Dyna-Q and Dyna-Q+ algorithms.

Report repository

Releases

No releases published

Packages

No packages published

Languages