Learning Graphical Models
Bayesian Adaptive Calibration and Optimal Design
BACON allows computational resources to be focused on simulations that provide the most value in terms of reducing epistemic uncertainty.
Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
In this paper, we show that partner specialization, in addition to diversity, is crucial for the robustness of a downstream generalist agent.
Reference-Based POMDPs
A Partially Observable Markov Decision Process (POMDP) is a general framework for the above problem.
QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Causal discovery is essential for understanding relationships among variables of interest in many scientific domains. In this paper, we focus on permutation-based methods for learning causal graphs in Linear Gaussian Acyclic Models (LiGAMs), where the permutation encodes a causal ordering of the variables. Existing methods in this setting do not scale due to their high computational complexity.
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
The interaction is usually modeled as Markov Decision Processes (MDPs). Research on MDPs can be broadly divided into two lines based on the reward generation mechanism. The first line of work [Jaksch et al., 2010, Azar et al., 2013, 2017, He et al., 2021] considers the
