Researchers across cognitive, neuro-and computer sciences increasingly reference 'human-
like'artificial intelligence and 'neuroAI'. However, the scope and use of the terms are often …

Recently an influx of studies claims emergent cognitive abilities in large language models
(LLMs). Yet, most rely on anecdotes, overlook contamination of training sets, or lack …

Agents must be able to adapt quickly as an environment changes. We find that existing
model-based reinforcement learning agents are unable to do this well, in part because of …

We introduce a principled method for performing zero-shot transfer in reinforcement learning
(RL) by exploiting approximate models of the environment. Zero-shot transfer in RL has …

Recent investigation on reinforcement learning (RL) has demonstrated considerable
flexibility in dealing with various problems. However, such models often experience difficulty …

World models power some of the most efficient reinforcement learning algorithms. In this
work, we showcase that they can be harnessed for continual learning–a situation when the …

The average-reward formulation is a natural and important formulation of learning and
planning problems, yet has received much less attention than the episodic and discounted …

Most of the current recommendation algorithms based on reinforcement learning are biased
towards the design of exploration strategies at the model level, ignoring the full use of …

One of the key behavioral characteristics used in neuroscience to determine whether the
subject of study—be it a rodent or a human—exhibits model-based learning is effective …

One of the key behavioral characteristics used in neuroscience to determine whether the
subject of study---be it a rodent or a human---exhibits model-based learning is effective …