Offline Reinforcement learning is commonly used for sequential
decision-...
Off-policy evaluation (OPE) aims to estimate the benefit of following a
...
Discount regularization, using a shorter planning horizon when calculati...
Decision-focused (DF) model-based reinforcement learning has recently be...
In safety-critical decision-making scenarios being able to identify
wors...
We develop a Reinforcement Learning (RL) framework for improving an exis...
Assessing the effects of a policy based on observational data from a
dif...
Identifying meaningful and independent factors of variation in a dataset...
Probabilistic models help us encode latent structures that both model th...
Machine learning models that utilize patient data across time (rather th...
We propose SLTD (`Sequential Learning-to-Defer') a framework for
learnin...
Estimating an individual's potential response to interventions from
obse...
We propose Preferential MoE, a novel human-ML mixture-of-experts model t...
Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease c...
Symmetry transformations induce invariances and are a crucial building b...
Deep models have advanced prediction in many domains, but their lack of
...
The lack of interpretability remains a barrier to the adoption of deep n...
Estimating the causal effects of an intervention in the presence of
conf...
Computer vision tasks are difficult because of the large variability in ...
Estimating causal effects in the presence of latent confounding is a
fre...
The lack of interpretability remains a key barrier to the adoption of de...
This paper considers a Bayesian view for estimating a sub-network in a M...