GSSI course on Reinforcement Learning
Next June Prof. Marcello Restelli (Politecnico, Milan) will give a course of 15 hours on Reinforcement Learning according to the following schedule:
Monday 15, Wednesday 17, Friday 19, Monday 22, Wednesday 24 June, every morning from 10 am to 1 pm.
The list of the covered topics is given below.
Monday 15, Wednesday 17, Friday 19, Monday 22, Wednesday 24 June, every morning from 10 am to 1 pm.
The course can be attended on zoom at the following link:
The list of the covered topics is given below.
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
The course will introduce the main modeling frameworks, will analyze the most relevant reinforcement–
1) Models
* Finite Markov Decision Processes
* Continuous Markov Decision Processes
* Partially Observable Markov Decision Processes
* Semi Markov Decision Processes
* Markov Games
* 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
3) Applications
* Autonomous driving
* Robot Control
* Water Resources Management
* Portfolio Management
Davide Di Ruscio
0
