Related papers: Open-Ended Learning Leads to Generally Capable Age…

The key challenge in multiagent learning is learning a best response to the behaviour of other agents, which may be non-stationary: if the other agents adapt their strategy as well, the learning target moves. Disparate streams of research…

Training agents to act competently in complex 3D environments from high-dimensional visual information is challenging. Reinforcement learning is conventionally used to train such agents, but requires a carefully designed reward function,…

In order to deploy autonomous agents to domains such as autonomous driving, infrastructure management, health care, and finance, they must be able to adapt safely to unseen situations. The current approach in constructing such agents is to…

Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Such agents need to create and represent goals, select which ones to pursue and learn to achieve them. Recent…

Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where…

Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications.…

We tackle a task where an agent learns to navigate in a 2D maze-like environment called XWORLD. In each session, the agent perceives a sequence of raw-pixel frames, a natural language command issued by a teacher, and a set of rewards. The…

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these…

Embodied agents struggle to generalize to new environments, even when those environments share similar underlying structures to their training settings. Most current approaches to generating these training environments follow an open-loop…

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable…

The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence. Intrinsically Motivated Goal Exploration Processes give learning agents a…

For over a decade now, robotics and the use of artificial agents have become a common thing.Testing the performance of new path finding or search space optimization algorithms has also become a challenge as they require simulation or an…

Autonomous vehicles are suited for continuous area patrolling problems. However, finding an optimal patrolling strategy can be challenging for many reasons. Firstly, patrolling environments are often complex and can include unknown…

Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition…

Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models to programmatically generate diverse environments, these…

An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills over a long lifetime could advance the frontier of artificial intelligence capabilities. The design of such agents, which remains a long-standing…

To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure…

Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data,…

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…