As robots and other intelligent agents move from simple environments and problems to more
complex, unstructured settings, manually programming their behavior has become …

Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an
agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a …

In this paper, we propose a novel edge-labeling graph neural network (EGNN), which
adapts a deep neural network on the edge-labeling graph, for few-shot learning. The …

Deep reinforcement learning has produced many success stories in recent years. Some
example fields in which these successes have taken place include mathematics, games …

Many real-world analytics problems involve two significant challenges: prediction and
optimization. Because of the typically complex nature of each challenge, the standard …

This paper presents OptNet, a network architecture that integrates optimization problems
(here, specifically in the form of quadratic programs) as individual layers in larger end-to-end …

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated
negotiation skills with other road users when overtaking, giving way, merging, taking left and …

This paper presents the input convex neural network architecture. These are scalar-valued
(potentially deep) neural networks with constraints on the network parameters such that the …

We present a simple and effective scheme for dependency parsing which is based on
bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector …

Abstract Machine learning pipelines often rely on optimizers procedures to make discrete
decisions (eg, sorting, picking closest neighbors, or shortest paths). Although these discrete …