research
∙
12/17/2021
An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations
Reinforcement learning agents perform well when presented with inputs wi...
share
research
∙
04/27/2020
Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems
Rapid online adaptation to changing tasks is an important problem in mac...
research
∙
09/21/2019
Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
This paper introduces the modulated Hebbian plus Q network architecture ...
research
∙
06/10/2019
Generative Continual Concept Learning
After learning a concept, humans are also able to continually generalize...
research
∙
03/06/2019
Using World Models for Pseudo-Rehearsal in Continual Learning
The utility of learning a dynamics/world model of the environment in rei...
research
∙
03/02/2019