In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

Imagine Genghis Khan, Aretha Franklin, and the Cleveland Cavaliers performing an opera
on Maui. This silly sentence makes a serious point: As humans, we can flexibly generate …

Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are
simultaneously learned by a shared model. Such approaches offer advantages like …

Transfer learning has recently become the dominant paradigm of machine learning. Pre-
trained models fine-tuned for downstream tasks achieve better performance with fewer …

Citing opinions is a powerful yet understudied strategy in argumentation. For example, an
environmental activist might say," Leading scientists agree that global warming is a serious …

Compositionality is a key strategy for addressing combinatorial complexity and the curse of
dimensionality. Recent work has shown that compositional solutions can be learned and …

Realtime environments change even as agents perform action inference and learning, thus
requiring high interaction frequencies to effectively minimize long-term regret. However …

In natural language inference (NLI), contexts are considered veridical if they allow us to infer
that their underlying propositions make true claims about the real world. We investigate …

The notion of equality (identity) is simple and ubiquitous, making it a key case study for
broader questions about the representations supporting abstract relational reasoning …

The options framework is a popular approach for building temporally extended actions in
reinforcement learning. In particular, the option-critic architecture provides general purpose …