Course on Reinforcement Learning
Course on Reinforcement Learning
Abstract
Introduction to the models and mathematical tools used in formalizing the problem of learning and decision-making under uncertainty. In particular, we will focus on the frameworks of reinforcement learning and multi-arm bandit. The main topics studied during the course are:
-Historical multi-disciplinary basis of reinforcement learning
-Markov decision processes and dynamic programming
-Stochastic approximation and Monte-Carlo methods
-Introduction to stochastic and adversarial multi-arm bandit
-Approximate dynamic programming
Where and When
The course on “Reinforcement Learning” will be held at the Ecole Centrale de Lille. The room for lectures is B7-14 and for the practical sessions is C016.
Schedule
See hyperplanning.
Lectures
News
• Text of the first Homework: homework1-tree.pdf
• Text of the second Homework: homework2.pdf code.zip
• Text of the third Homework: homework3.pdf code.zip
• Schedule for the presentations: schedule.pdf
Proposed papers to review
RULES: Students should work in pairs and prepare a presentation of 15 minutes on two papers (one paper is also acceptable if particularly long) chosen in the following list.
•“An Intelligent Battery Controller Using Bias-Corrected Q-learning”
•“An Approximate Dynamic Programming Algorithm for Large-Scale Fleet Management: A Case Application”
•“A Contextual-Bandit Approach to Personalized News Article Recommendation”
•“Autonomous inverted helicopter flight via reinforcement learning”
•“Reinforcement Learning-based Control of Traffic Lights in Non-stationary Environments”
•“Optimizing Dialogue Management with Reinforcement Learning”
•“Coadaptive Brain–Machine Interface via Reinforcement Learning”
•“RL-MAC: a reinforcement learning based MAC protocol for wireless sensor networks”
•“Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems”
•“Interactive Selection of Visual Features through Reinforcement Learning”
•“Approximate Dynamic Programming Finally Performs Well in the Game of Tetris”
•John Moody and Matthew Saffell. Learning to trade via direct reinforcement, 2001
•Beomsoo Park and Benjamin Van Roy. Adaptive execution: Exploration and learning of price impact
•Ying Tan, Wei Liu, and Qinru Qiu. Adaptive power management using reinforcement learning
•J. Mary, R. Gaudel, Ph. Preux, Bandits Warm-up Cold Recommender Systems
•