Scientific computing has experienced a surge empowered by advancements i...
A well-defined reward function is crucial for successful training of an
...
Using reinforcement learning for automated theorem proving has recently
...
We present AutoDOViz, an interactive user interface for automated decisi...
Explainability of Reinforcement Learning (RL) policies remains a challen...
In complex tasks where the reward function is not straightforward and
co...
This paper introduces Logical Credal Networks, an expressive probabilist...
The pipeline optimization problem in machine learning requires simultane...
Dialogue systems have many applications such as customer support or ques...
Inspired by the recently introduced framework of AND/OR search spaces fo...
The paper continues the study of partitioning based inference of heurist...
We describe multi-objective influence diagrams, based on a set of p
obje...
In this paper, we develop a qualitative theory of influence diagrams tha...