Reinforcement Learning is an area of Machine Learning aiming at providing an agent with optimal
decision abilities based on experience given in terms of future rewards.
News-breaking successes in applications such as Atari games, Go, Poker, etc., where software defeated best
human players, significantly increased public attention and scientific research around this topic.
In this seminar, we will discuss the main ideas, challenges, algorithms and open problems related to (deep) reinforcement learning. Specifically, we will focus on real examples and we will provide practical hints and solutions to apply RL on multiple problems, ranging from video-games to robot control.
20/02/2019
Il seminario sarà tenuto dal Prof. Luca Iocchi, alle ore 15:00 e si terrà nell'auletta didattica della palazzina E del DIMA
Short bio:
Prof. Luca Iocchi (M) (www.dis.uniroma1.it/~iocchi) is Associate Professor at Sapienza University of Rome, Italy. His main research interests include cognitive robotics, action planning, multi-robot coordination, robot perception, robot learning, sensor data fusion. He is author of more than 100 referred papers (h-index 37 [Google scholar]) in journals and conferences in artificial intelligence and robotics, member of the program committee of several conferences (IJCAI, AAAI, AAMAS, ICRA, IROS), guest editor for journal special issues and reviewer for many journals in the field. He has been principal investigator of many international projects in different research fields, including domestic and social robots, intelligent systems and multi-robot for surveillance, robot benchmarking and competitions. In particular, he has supervised the development of teams participating to robotic competitions, such as RoboCup soccer, RoboCup rescue, RoboCup@Home. He also contributed to benchmarking domestic service robots through scientific competitions within RoboCup@Home, of which he has been member of the Executive Committee from 2008 to 2013. He is currently member of the Board of Trustees of the RoboCup Federation.