Related papers: Adapting to Unseen Environments through Explicit R…

In order to deploy autonomous agents in digital interactive environments, they must be able to act robustly in unseen situations. The standard machine learning approach is to include as much variation as possible into training these agents.…

Regardless of past learning, an agent in an open world will face unfamiliar events outside of prior experience, existing models, or policies. Further, the agent will sometimes lack relevant knowledge and/or sufficient time to assess the…

In real-world environments, AI systems often face unfamiliar scenarios without labeled data, creating a major challenge for conventional scene understanding models. The inability to generalize across unseen contexts limits the deployment of…

Automated planning technology has developed significantly. Designing a planning model that allows an automated agent to be capable of reacting intelligently to unexpected events in a real execution environment yet remains a challenge. This…

Self-adaptive systems continuously adapt to changes in their execution environment. Capturing all possible changes to define suitable behaviour beforehand is unfeasible, or even impossible in the case of unknown changes, hence human…

Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…

The ability to learn a model is essential for the success of autonomous agents. Unfortunately, learning a model is difficult in partially observable environments, where latent environmental factors influence what the agent observes. In the…

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.…

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky…

Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…

Multi-agent trajectory forecasting in autonomous driving requires an agent to accurately anticipate the behaviors of the surrounding vehicles and pedestrians, for safe and reliable decision-making. Due to partial observability in these…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

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…

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…

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…

A grand goal in AI is to build a robot that can accurately navigate based on natural language instructions, which requires the agent to perceive the scene, understand and ground language, and act in the real-world environment. One key…

Research interest in autonomous agents is on the rise as an emerging topic. The notable achievements of Large Language Models (LLMs) have demonstrated the considerable potential to attain human-like intelligence in autonomous agents.…

This paper targets control problems that exhibit specific safety and performance requirements. In particular, the aim is to ensure that an agent, operating under uncertainty, will at runtime strictly adhere to such requirements. Previous…