Learning Graphical Models
Finding good policies in average-reward Markov Decision Processes without prior knowledge
Reinforcement learning (RL) is a paradigm in which an agent interacts with its environment, modeled as a Markov Decision Process (MDP), by taking actions and observing rewards.
Amortized Bayesian Experimental Design for Decision-Making
For example, in personalized medical diagnostics, a model is built based on historical data to facilitate an optimal treatment for a new patient (Bica et al., 2021).
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects Alexander W. Levis
To fill this gap, we introduce a nonparametric causal inference framework for analyzing "closed-loop" designs, which use
Vision-Language Navigation with Energy-Based Policy
Existing VLN models are optimized through expert demonstrations by supervised behavioural cloning or incorporating manual reward engineering.
c2f71567cd53464161cab3336e8fc865-Paper-Datasets_and_Benchmarks_Track.pdf
Furthermore, extensive analysis ( 4.3) on Spider2-V demonstrate that these strategies remarkably
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
Diffusion-based generative models, as first introduced by Sohl-Dickstein et al. (2015), have shown
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
Recent works in V ariational Inference have examined alternative criteria to the commonly used exclusive Kullback-Leibler divergence.
