Multiagent learning settings are inherently more difficult than single-a...
The main challenge of multiagent reinforcement learning is the difficult...
The mixing time of the Markov chain induced by a policy limits performan...
Hierarchical reinforcement learning has focused on discovering temporall...
In this article, we aim to provide a literature review of different
form...
This paper introduces an information-theoretic constraint on learned pol...
A fundamental challenge in multiagent reinforcement learning is to learn...
Biological agents learn and act intelligently in spite of a highly limit...
Compositional and relational learning is a hallmark of human intelligenc...
The difficulty of classical planning increases exponentially with search...
The options framework is a popular approach for building temporally exte...
Option-critic learning is a general-purpose reinforcement learning (RL)
...
Compositionality is a key strategy for addressing combinatorial complexi...
Despite remarkable successes achieved by modern neural networks in a wid...
Heterogeneous knowledge naturally arises among different agents in
coope...
Lack of performance when it comes to continual learning over non-station...
Building systems that autonomously create temporal abstractions from dat...
Given the emerging global threat of antimicrobial resistance, new method...
We present a framework and algorithm for peer-to-peer teaching in cooper...
Given the recent success of Deep Learning applied to a variety of single...
Deep lifelong learning systems need to efficiently manage resources to s...
Multi-task learning (MTL) with neural networks leverages commonalities i...
Although neural networks are well suited for sequential transfer learnin...