Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
This lecture covers advanced topics in machine learning, focusing on reinforcement learning (RL). The instructor explains RL policies, models of the world, optimal policy finding, value functions, V-Q-value functions, Bellman recursion, and discount factors. Exercises involve drawing optimal policies in gridworlds. The lecture also delves into different update rules in dynamic programming, Monte Carlo sampling, and on-policy TD control. It discusses offline vs. online search, combining RL with supervised learning, and the importance of realistic simulators. The session concludes with a summary of RL concepts and their applications.