Skip to content

Evaluating EGT and RL dynamics in 3 strategies norm games

Notifications You must be signed in to change notification settings

Giovanni3A/LearningDynamics

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Learning Dynamics


Abstract

Simluation module of different model dynamics applied to simple norm games. Each dynamics is defined by it's differential equation, derived from the model.

Structure

├── README.md                                  
├── .gitignore                                 
├── requirements.txt                           <- List of necessary packages
├── examples                                   <- Examples of use, notebooks and generated data
├── LDynamics                                  <- Folder with main scripts
    ├── _dynamic_simulator.py                      <- Simulation method

Results

As analysis results, we can compare how different methods develop strategies in games. The HawksDoves example uses the Hawks and Doves game (https://en.wikipedia.org/wiki/Chicken_(game)) and show how the methods converge to different states in different ways.

replicator.png

ppo.png

References

https://arxiv.org/pdf/1906.00190.pdf

https://www.ssc.wisc.edu/~whs/research/egt.pdf

About

Evaluating EGT and RL dynamics in 3 strategies norm games

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages