Learning Graphical Models
Reinforcement Learning with L TL and ω-Regular Objectives via Optimality-Preserving Translation to Average Rewards Xuan-Bach Le
In this work, we study the relationship between these objectives.
Label Noise: Ignorance Is Bliss
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift.
Agent Planning with World Knowledge Model
Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric W orld K nowledge M odel ( WKM) to facilitate agent
Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
Utilizing mutual learning can effectively enhance the performance of peer BNNs.
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Critical in this context is the prior knowledge accumulated from related tasks.
Rehearsal Learning for Avoiding Undesired Future
Machine learning (ML) models have been widely used to make predictions.