8000 GitHub - entangledqubit0110/Pong-RL-PLE: RL agents to play Pong using PLE and pygame environment
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

entangledqubit0110/Pong-RL-PLE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

50 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Installing pygame and the learning environment

pip install pygame

git clone https://github.com/ntasfi/PyGame-Learning-Environment

cd PyGame-Learning-Environment

sudo pip install -e .

Training the agents

python3 train_<agent>.py

Testing the agents

For testing we need to change the number of bins appropriately according to the details.txt.

python3 test_<agent>.py --param_file=<path_to_finalQvalue_file>

  <Agent>                 <path_to_finalQvalue_file>
  
    mc                       mc_results/1/final_Q.log

   sarsa                    sarsa_results/2/final_Q.log
   
  td_lambda                 td_forward_results/1/final_Q.log

   td_zero                   td_zero_results/final_Q.log

About

RL agents to play Pong using PLE and pygame environment

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  
0