RL Odyssey 1: Intro to Reinforcement Learning
Details
Reinforcement Learning (RL) stands as a cornerstone in the realm of artificial intelligence, offering powerful techniques for agents to learn optimal behavior through interaction with their environment. In this introductory talk, we embark on a journey through the fundamental principles of RL, exploring its core concepts such as Markov Decision Processes (MDPs), value functions, and the delicate balance between exploration and exploitation. We delve into the methodologies of Monte Carlo methods and Temporal Difference Learning, unraveling their mechanisms for policy evaluation and action selection. Additionally, we introduce the innovative Monte Carlo Tree Search (MCTS) algorithm, shedding light on its pivotal role in decision-making under uncertainty. Throughout the discourse, we uncover the applications of RL across diverse domains, from game playing to robotics, while contemplating the intriguing vistas it unveils for the future of intelligent systems.
L'evento inizia alle 18:00, il talk inizia alle 18:30.
Speaker:Alberto Righetti & Lorenzo Bonanni
Aula: T04
REGISTRAZIONE:
https://www.eventbrite.it/e/888307610977