GitHub - deloroy/Reinforcement-Learning: Project : Subgoal Discovery on the Taxi Domain with Macro Q-Learning. Practicals : Q-Leaning, Bandits (MAB, LinUCB), Approximate RL. For the RL course (Master MVA).

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
1 - Q-Learning		1 - Q-Learning
2 - Multi-Armed and Linear Bandits		2 - Multi-Armed and Linear Bandits
3 - Approximate RL (REINFORCE and Fitted Q-Iteration)		3 - Approximate RL (REINFORCE and Fitted Q-Iteration)
Subgoal Discovery Project		Subgoal Discovery Project

About

Project : Subgoal Discovery on the Taxi Domain with Macro Q-Learning. Practicals : Q-Leaning, Bandits (MAB, LinUCB), Approximate RL. For the RL course (Master MVA).