Deep Learning
Deep Contract Design via Discontinuous Networks
Contract theory studies the setting where a principal seeks to design a contract for rewarding an agent on the basis of the uncertain outcomes caused by the agent's private actions [
ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
In partially observable (PO) environments, how to infer unseen information from raw observations puzzled the agents.
Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds
As a significant direction in this line, hyperbolic representation learning has been shown to offer several advantages over conventional Euclidean geometry.
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content.
Graph Learning for Numeric Planning Dillon Z. Chen
In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks.
