GitHub / apashwinkumar / optimal-path-qlearning
Optimal pathfinding with Q-Learning and Double Q-Learning in large grids, using reward shaping and decaying epsilon; compares to Dijkstra. 🐙
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apashwinkumar%2Foptimal-path-qlearning
PURL: pkg:github/apashwinkumar/optimal-path-qlearning
Stars: 0
Forks: 0
Open issues: 0
License: mit
Language: Python
Size: 1.48 MB
Dependencies parsed at: Pending
Created at: 18 days ago
Updated at: 18 days ago
Pushed at: 18 days ago
Last synced at: 18 days ago
Topics: deep-learning, dijkstra, epsilon-greedy, optimal-path, python, random-selection, reinforcement-learning, spyder-python-ide