Machine intelligence

Deep Neural Networks (DNNs) are known to be brittle to even minor distribution shifts compared to the training distribution . Simplicity Bias (SB) of DNNs – bias towards learning a small number of simplest features – has been demonstrated to be a key reason for this brittleness. Prior works have shown that the effect of Simplicity Bias is extreme – even when the features learned are diverse,...

As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting, with most methods regularizing either the actor or the critic. These methods appear distinct. Actor regularization (e.g., behavioral cloning penalties) is simpler and has appealing convergence properties, while critic regularization typically requires...

Mean-field games have been used as a theoretical tool to obtain an approximate Nash equilibrium for symmetric and anonymous $N$-player games in literature. However, limiting applicability, existing theoretical results assume variations of a ``population generative model'', which allows arbitrary modifications of the population distribution by the learning algorithm. Instead, we show that $N$...

Mirror descent value iteration (MDVI), an abstraction of Kullback--Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performing practical RL algorithms. However, despite the use of function approximation in practice, the theoretical understanding of MDVI has been limited to tabular Markov decision processes (MDPs). We study MDVI with...