Machine learning has long since become a keystone technology, accelerating science and
applications in a broad range of domains. Consequently, the notion of applying learning …

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is
widely recognized as one of the key challenges of modern AI. Recent years have seen a …

It has been recently shown that general policies for many classical planning domains can be
expressed and learned in terms of a pool of features defined from the domain predicates …

This work exploits action equivariance for representation learning in reinforcement learning.
Equivariance under actions states that transitions in the input space are mirrored by …

While reinforcement learning methods have delivered remarkable results in a number of
settings, generalization, ie, the ability to produce policies that generalize in a reliable and …

We consider the problem of learning generalized policies for classical planning domains
using graph neural networks from small instances represented in lifted STRIPS. The …

In robotic domains, learning and planning are complicated by continuous state spaces,
continuous action spaces, and long task horizons. In this work, we address these challenges …

Natural language-conditioned reinforcement learning (RL) enables agents to follow human
instructions. Previous approaches generally implemented language-conditioned RL by …

One of the main obstacles for developing flexible AI systems is the split between data-based
learners and model-based solvers. Solvers such as classical planners are very flexible and …

We achieved a new milestone in the difficult task of enabling agents to learn about their
environment autonomously. Our neuro-symbolic architecture is trained end-to-end to …