Skip to content

Approaches for inhibiting selfish behaviour of RL-based agents, in environments which encourage it. BSc CompSci dissertation.

License

Notifications You must be signed in to change notification settings

cemiu/inhibit-selfish-rl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

inhibit-selfish-rl

Studying and comparing approaches for inhibiting selfish behaviour of RL-based agents, in environments which encourage it.

This codebase was used for my final year dissertation, as part of my BSc CompSci degree in 2022/23.

Description

Four multi-agent environments are evaluated, where two agents with not-relating or opposing goals exist.

The optimal policy for agent A is not aligned with agent B's goals.

This project compares three approaches for inhibiting selfish behaviour:

  • Add B's reward function to A's reward function, with some multiplier
  • Devise custom, per-environment, heuristics for reducing selfish behaviour
  • Use Inverse Reinforcement Learning to approximate B's goals, then add them to A's reward function

More info

If you want to learn more, you can check out this poster, or presentation (Apple Keynotes), presentation (PDF, but without videos), or just read the unnecessarily long dissertation I wrote about it.

Setup

At the time of creation, these commands worked for setting up all dependencies. With SB3 moving to gymnasium & imitation planning to later do the same, this is unlikely to work anymore.

pip install opencv-python matplotlib pandas seaborn tensorboard numpy imitation jupyter pip install git+https://github.com/carlosluis/stable-baselines3@fix_tests

imitation=1.1.1

About

Approaches for inhibiting selfish behaviour of RL-based agents, in environments which encourage it. BSc CompSci dissertation.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published