Large Language Models (LLMs) have emerged as powerful tools capable of
a...
An important problem in reinforcement learning is designing agents that ...
Procedural content generation (PCG) is a growing field, with numerous
ap...
In this work, we tackle the problem of open-ended learning by introducin...
In this work, we consider the problem of procedural content generation f...
We propose world value functions (WVFs), a type of goal-oriented general...
A major challenge in reinforcement learning is specifying tasks in a man...
An open problem in artificial intelligence is how to learn and represent...
In this work, we investigate the properties of data that cause popular
r...
We are concerned with the question of how an agent can acquire its own
r...
Using function approximation to represent a value function is necessary ...
We present a framework that, given a set of skills a robot can perform,
...
Procedurally generated video game content has the potential to drastical...
Learning disentangled representations with variational autoencoders (VAE...
Graph neural networks (GNNs) build on the success of deep learning model...
With increasing interest in procedural content generation by academia an...
We propose a framework that learns to execute natural language instructi...
We present a method for learning options from segmented demonstration
tr...
Deep neural networks are typically too computationally expensive to run ...
We propose a framework for defining a Boolean algebra over the space of
...
Pre-training a deep neural network on the ImageNet dataset is a common
p...
We present a framework for autonomously learning a portable representati...
An important property for lifelong-learning agents is the ability to com...