Catastrophic interference is common in many network-based learning syste...
In this work, we consider the off-policy policy evaluation problem for
c...
Compared to fixed-function switches, the flexibility of programmable swi...
Cloud data centers are rapidly evolving. At the same time, large-scale d...
The performance of reinforcement learning (RL) agents is sensitive to th...
In this paper we investigate the properties of representations learned b...
Self-supervised learning algorithms, including BERT and SimCLR, have ena...
Offline reinforcement learning-learning a policy from a batch of data-is...
Continuously monitoring a wide variety of performance and fault metrics ...
This paper introduces Beldi, a library and runtime system for writing an...
Catastrophic interference is common in many network-based learning syste...
Clinical researchers often select among and evaluate risk prediction mod...
Temporal difference methods enable efficient estimation of value functio...
Central Pattern Generators (CPGs) are biological neural circuits capable...
We investigate sparse representations for control in reinforcement learn...
Attribute-aware CF models aims at rating prediction given not only the
h...
A perennial question in computer networks is where to place functionalit...