Skip to content

Project for Artificial Intelligence course at University of Ljubljana, Faculty of Computer and Information science.

License

Notifications You must be signed in to change notification settings

lukau2357/bipedal-walker-td3

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project description

Implementation of the TD3 - twin delayed DDPG algorithm for reinforcement learning (original publication link), particularlly usefull for continuous action space-continuous state space problems.

The algorithm was tested on the BipedalWalker-v3 environment. In order to evaluate the variability of this algorithm, we trained 15 different agents on a high-performance GPU with CUDA for 550 episodes. We recorded the obtained reward by each agent, and obtained the following results:

ci_plot

The learning process can be observed on the following video: run_simulation

Technical details about the algorithm can be found in the acompanying report.

About

Project for Artificial Intelligence course at University of Ljubljana, Faculty of Computer and Information science.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Languages