Neuroevolution in deep neural networks: Current trends and future challenges
A variety of methods have been applied to the architectural configuration and learning or
training of artificial deep neural networks (DNN). These methods play a crucial role in the …
training of artificial deep neural networks (DNN). These methods play a crucial role in the …
The child as hacker
The scope of human learning and development poses a radical challenge for cognitive
science. We propose that developmental theories can address this challenge by adopting …
science. We propose that developmental theories can address this challenge by adopting …
First return, then explore
Reinforcement learning promises to solve complex sequential-decision problems
autonomously by specifying a high-level reward function only. However, reinforcement …
autonomously by specifying a high-level reward function only. However, reinforcement …
Bio-inspired computation: Where we stand and what's next
In recent years, the research community has witnessed an explosion of literature dealing
with the mimicking of behavioral patterns and social phenomena observed in nature towards …
with the mimicking of behavioral patterns and social phenomena observed in nature towards …
Aps: Active pretraining with successor features
We introduce a new unsupervised pretraining objective for reinforcement learning. During
the unsupervised reward-free pretraining phase, the agent maximizes mutual information …
the unsupervised reward-free pretraining phase, the agent maximizes mutual information …
Go-explore: a new approach for hard-exploration problems
A Ecoffet, J Huizinga, J Lehman, KO Stanley… - ar** elites
Many fields use search algorithms, which automatically explore a search space to find high-
performing solutions: chemists search through the space of molecules to discover new …
performing solutions: chemists search through the space of molecules to discover new …
Paired open-ended trailblazer (poet): Endlessly generating increasingly complex and diverse learning environments and their solutions
While the history of machine learning so far largely encompasses a series of problems
posed by researchers and algorithms that learn their solutions, an important question is …
posed by researchers and algorithms that learn their solutions, an important question is …