黑料福利网

Andrea Agazzi, Assistant Professor in the Mathematics Department at the University of Pisa, is a guest of Mauro Salazar, Assistant Professor at Control Systems Technology group of the department of Mechanical Engineering, 黑料福利网.

Title  |  Nonlinear policy optimization in deep reinforcement learning: policy gradients for wide neural networks 

In recent years, we have witnessed multiple groundbreaking results obtained using neural networks as flexible (nonlinear) parameterizations of large policy classes to solve difficult reinforcement learning tasks, e.g., AlphaGO, Dota2, Self-driving cars. However, despite these successes, there exists a notable gap in providing theoretical explanations for the effectiveness of neural networks trained with (deep) reinforcement learning algorithms. In this presentation, I will first briefly overview of the policy optimization problem in reinforcement learning, along with an introduction to the policy gradient algorithm, a prototypical solution approach. Then, I will discuss some limitations of this algorithm when paired with general nonlinear policy classes. Finally, I will discuss how these limitations are bypassed by wide neural networks under an appropriate scaling of parameters at initialization, resulting in the convergence of the policy gradient training dynamics towards a so-called 鈥渕ean-field鈥� limit. In particular, in this setting one can prove global optimality of the dynamics' fixed points despite the nonlinear and nonconvex characteristics of the risk function. 

Program
12:00 - 12.45   Lecture in Gemini South 0.05 (doors open at 11:45)
12:45 - 13:00   Q&A
13:00                    Pizza lunch