Skip to content

End-to-end reinforcement learning using DDPG and PPO algorithms in a simulated robot environment

Notifications You must be signed in to change notification settings

jjurm/path-following-reinforcement-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

56 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning for Path Following

Consider the task of a problem attempting to follow a path in a constrained environment with only a few lines to follow. We attempt this using end-to-end reinforcement learning and explore two algorithms for doing so: Deep Deterministic Policy Gradients (DDPG) and Proximal Policy Optimisation (PPO). We further explore different problem formulations to learn a path-following controller or the velocities of the agent directly, and report our findings.

Report

The PDF containing the project's Report can be found here.

Presentation slides

Slides used for the project's presentation can be found here.

Authors

About

End-to-end reinforcement learning using DDPG and PPO algorithms in a simulated robot environment

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages