Psychologists and neuroscientists extensively rely on computational models for studying
and analyzing the human mind. Traditionally, such computational models have been hand …

Training reinforcement learning (RL) agents on robotic tasks typically requires a large
number of training samples. This is because training data often consists of noisy trajectories …

As trajectories sampled by policies used by reinforcement learning (RL) and generative flow
networks (GFlowNets) grow longer, credit assignment and exploration become more …

World models can represent potentially high-dimensional pixel observations in compact
latent spaces, making it tractable to model the dynamics of the environment. However, the …

Identifying goal-relevant features in novel environments is a central challenge for efficient
behaviour. We asked whether humans address this challenge by relying on prior knowledge …

Humans represent scenes and objects in rich feature spaces, carrying information that
allows us to generalise about category memberships and abstract functions with few …

We are encouraged by the many positive commentaries on our target article. In this
response, we recapitulate some of the points raised and identify synergies between them …

To solve control problems via model-based reasoning or planning, an agent needs to know
how its actions affect the state of the world. The actions an agent has at its disposal often …

Generalizing from only two time series towards unseen intermediate patterns poses a
significant challenge in representation learning. In this paper, we introduce a novel …