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 Graph Search.
This lecture covers the fundamentals of reinforcement learning, starting with Markov processes and policy optimization. Topics include Markov properties, time evolution in Markov processes, decision rules, and policy optimization techniques such as parameterization and gradient ascent. The lecture also discusses convergence to the optimal policy, estimation of expected values, and the challenges of reinforcement learning methods. Emphasis is placed on understanding Markov processes, optimizing policies, and the trade-offs involved in reinforcement learning algorithms.