GitHub / Develop-Packt / Solving-the-Multi-Armed-Bandit-Problem
This module discusses the multi armed bandit problem and various strategies to solve it, introducing the concepts of state-rewards functions in RL and how to solve it using simple strategies
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Develop-Packt%2FSolving-the-Multi-Armed-Bandit-Problem
PURL: pkg:github/Develop-Packt/Solving-the-Multi-Armed-Bandit-Problem
Stars: 0
Forks: 1
Open issues: 0
License: mit
Language: Jupyter Notebook
Size: 1.41 MB
Dependencies parsed at: Pending
Created at: about 5 years ago
Updated at: about 5 years ago
Pushed at: about 5 years ago
Last synced at: over 2 years ago
Topics: ai, multi-armed-bandit, python, reinforcement-learning, tensorflow-2