GitHub / Pegah-Ardehkhani / Shortest-Path-using-Reinforcement-Learning
Solve the shortest path problem using Reinforcement Learning. This project applies RL techniques, such as Q-learning and SARSA(λ), to find optimal routes in a weighted graph, where the algorithm learns to navigate by receiving rewards based on edge distances.
Stars: 5
Forks: 0
Open issues: 0
License: apache-2.0
Language: Jupyter Notebook
Size: 215 KB
Dependencies parsed at: Pending
Created at: 5 months ago
Updated at: 2 months ago
Pushed at: 5 months ago
Last synced at: 25 days ago
Topics: q-learning, reinforcement-learning, reinforcement-learning-algorithms, sarsa, sarsa-lambda, shortest-path