Skip to content

Solving some gym env using policy based methods: hill climbing and Cross Entropy Method

Notifications You must be signed in to change notification settings

EyaRhouma/Policy_based_method

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Value based method

In this repository we're trying to solve 2 openAI Gym's env using two policy based methods: Hill climbing and Cross-Entropy method

Hill Climbing

Hill_Climbing.ipynb is an implementation of hill climbing with adaptive noise scaling for OpenAI Gym's Cartpole environment.

Result

Trained Agent

Cross-Entropy Method

CEM.ipynb is an implementation of the cross-entropy method for OpenAI Gym's MountainCarContinuous environment.

Result

Trained Agent

Additionals

For more well explained methods for policy based method here's a good blog:

http://kvfrans.com/simple-algoritms-for-solving-cartpole/

--> corresponding github: https://github.com/kvfrans/openai-cartpole

About

Solving some gym env using policy based methods: hill climbing and Cross Entropy Method

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published