Skip to content

danielliuce/CrossEntropyMethod

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 

Repository files navigation

ReinforcementLearningMethods (RL) Methods

CartPole Environement Problem

Proposed Problem: How to balance a stick without it falling by moving to the left or right. Refer to Figure in Issues->Images Cross Entropy Method applied on this problem, results of the RL model can be found underneath issues->images

Refer to Issues->Images (Figures 1-3) for RL Results

FrozenLake Environment Problem

Outline of problem: Agent lives in a grid of size 4 x 4 and can move in four directions: up, down, left, and right

Proposed Problem: Agent always starts at top-left position and its goal is to reach the bottom-right cell of the grid. (See Figure 4 for details) There are holes in the fixed cells of the grid and if agent falls into these holes, the episode ends If the agent reaches the destination cell then it an reward of 1.0 and the episode ends. The world is slippery, so agent's actions are unexpected

Refer to Issues->Images (Figures 5-7) for RL Results

About

This Repository is dedicated to my own self learning of the reinforcement learning method Cross-Entropy Method from the book Deep Reinforcement Learning Hands-On by Maxim Lapan with comments of my own

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages