Related papers: Integrating cognitive map learning and active infe…

We train an agent to navigate in 3D environments using a hierarchical strategy including a high-level graph based planner and a local policy. Our main contribution is a data driven learning based approach for planning under uncertainty in…

Humans construct internal cognitive maps of their environment directly from sensory inputs without access to a system of explicit coordinates or distance measurements. While machine learning algorithms like SLAM utilize specialized visual…

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

Although existing models can interact with humans and provide satisfactory responses, they lack the ability to act autonomously or engage in independent reasoning. Furthermore, input data in these models is typically provided as explicit…

A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly…

People often give instructions whose meaning is ambiguous without further context, expecting that their actions or goals will disambiguate their intentions. How can we build assistive agents that follow such instructions in a flexible,…

Active inference is emerging as a possible unifying theory of perception and action in cognitive and computational neuroscience. On this theory, perception is a process of inferring the causes of sensory data by minimising the error between…

Active search, in applications like environment monitoring or disaster response missions, involves autonomous agents detecting targets in a search space using decision making algorithms that adapt to the history of their observations.…

Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces.…

We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly…

We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the spatial and semantic variability of indoor environments.…

In multi-agent systems, agents possess only local observations of the environment. Communication between teammates becomes crucial for enhancing coordination. Past research has primarily focused on encoding local information into embedding…

Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting…

Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under…

Ambiguity poses a major challenge to large language models (LLMs) used as robotic planners. In this letter, we present Scene Graph-Chain-of-Thought (SG-CoT), a two-stage framework where LLMs iteratively query a scene graph representation of…

The human brain possesses the extraordinary capability to contextualize the information it receives from our environment. The entorhinal-hippocampal plays a critical role in this function, as it is deeply engaged in memory processing and…

Neural-based learning agents make decisions using internal artificial neural networks. In certain situations, it becomes pertinent that this knowledge is re-interpreted in a friendly form to both the human and the machine. These situations…

An embodied agent constantly influences its environment and is influenced by it. We use the sensorimotor loop to model these interactions and thereby we can quantify different information flows in the system by various information theoretic…

Complex robot behaviour typically requires the integration of multiple robotic and Artificial Intelligence (AI) techniques and components. Integrating such disparate components into a coherent system, while also ensuring global properties…

This study proposes a distributed algorithm that makes agents' adaptive grouping entrap multiple targets via automatic decision making, smooth flocking, and well-distributed entrapping. Agents make their own decisions about which targets to…