masoudslipknot/Reinforcment_Learning_ValueIteration

Reinforcement- Learning project: Value Iteration Implementation.

12
/ 100
Experimental

This project helps demonstrate how an autonomous agent learns the best path to achieve goals in a grid-like environment. You provide a map with rewards for reaching certain spots and penalties for going out of bounds. The output is a 'policy map' that tells the agent the optimal direction to move from any given square. This is useful for anyone studying basic artificial intelligence or reinforcement learning algorithms.

No commits in the last 6 months.

Use this if you are learning about or teaching the fundamentals of how an agent can learn optimal strategies in a simplified, grid-based world.

Not ideal if you need to apply reinforcement learning to complex, real-world problems with continuous states or actions.

artificial-intelligence-education reinforcement-learning-basics agent-pathfinding simulated-environments policy-optimization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

5

Forks

Language

Java

License

Last pushed

Feb 08, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/masoudslipknot/Reinforcment_Learning_ValueIteration"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.