GSSI course on Reinforcement Learning

Reinforcement learning deals with solving sequential decision-making problems when no (or minimal) prior information is available. Solving sequential decision-making problems means to find their optimal control policies.  Using reinforcement–learning algorithms, the optimal policy is learned through the direct interaction between the agent (or controller) and the system to be controlled.

 

The course will introduce the main modeling frameworks, will analyze the most relevant reinforcement–learning techniques, and, finally, some interesting applications of these techniques to real-world domains will be shown.

1) Models

* Finite Markov Decision Processes
* Continuous Markov Decision Processes
* Partially Observable Markov Decision Processes
* Semi Markov Decision Processes
* Markov Games

2) Algorithms
* Value Iteration based algorithms (Q-learning, SARSA, TD(lambda))
* Policy Iteration based algorithms (actor-critic methods, LSPI)
* Policy Search algorithms (policy gradient methods and stochastic search techniques)
* Exploration techniques (R-MAX, model-based Interval Estimation)
* Model-free vs Model-based algorithms
* Batch algorithms (Fitted Q-iteration)
* Function approximation in Reinforcement Learning algorithms

3) Applications
* Autonomous driving
* Robot Control
* Water Resources Management
* Portfolio Management