Natural policy gradient (NPG) methods, equipped with function approximation and entropy
regularization, achieve impressive empirical success in reinforcement learning problems …

Natural actor-critic (NAC) and its variants, equipped with the representation power of neural
networks, have demonstrated impressive empirical success in solving Markov decision …

In this article, we study the dynamics of temporal-difference (TD) learning with neural
network-based value function approximation over a general state space, namely, neural TD …

Overparameterization is one of the key techniques in modern machine learning, where a
model with the higher complexity can generalize better on test data against the common …

Existing risk-averse reinforcement learning approaches still face several challenges,
including the lack of global optimality guarantee and the necessity of learning from long-term …

In many learning problems, it is desirable to incorporate explicit regularization in the
objective to avoid overfitting the data. Typically, the regularized objective is solved via …

Existing risk-averse reinforcement learning approaches still face several challenges,
including the lack of global optimality guarantee and the necessity of learning from long-term …

We look at two facets of machine learning from a perspective of dynamical systems, that is,
the data generated from a dynamical system and the iterative inference algorithm posed as …