Related papers: Continual Developmental Neurosimulation Using Embo…
Continual learning is crucial for creating AI agents that can learn and improve themselves autonomously. A primary challenge in continual learning is to learn new tasks without losing previously learned knowledge. Current continual learning…
Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these…
Braitenberg vehicles could be mentioned as the seminal elements for cognitive studies in robotics fields especially neurorobotics to invent more smart robots. Motion detection of dynamic objects could be taken as one of the most inspiring…
Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge…
Despite advances in embodied AI, agent reasoning systems still struggle to capture the fundamental conceptual structures that humans naturally use to understand and interact with their environment. To address this, we propose a novel…
The concentration gradient of the Bicoid morphogen, which is established during the early stages of a Drosophila melanogaster embryonic development, determines the differential spatial patterns of gene expression and subsequent cell fate…
An agent-based model (ABM) is a computational model in which the local interactions of autonomous agents with each other and with their environment give rise to global properties within a given domain. As the detail and complexity of these…
Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the…
Developmental psychology and neuroimaging research identified a close link between numbers and fingers, which can boost the initial number knowledge in children. Recent evidence shows that a simulation of the children's embodied strategies…
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in…
A few decades of work in the AI field have focused efforts on developing a new generation of systems which can acquire knowledge via interaction with the world. Yet, until very recently, most such attempts were underpinned by research which…
The Integrated Information Theory provides a quantitative approach to consciousness and can be applied to neural networks. An embodied agent controlled by such a network influences and is being influenced by its environment. This involves,…
The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample…
Evolutionary Computation has been successfully used to synthesise controllers for embodied agents and multi-agent systems in general. Notwithstanding this, continuous on-line adaptation by the means of evolutionary algorithms is still…
This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and…
We develop a learning-based algorithm for the distributed formation control of networked multi-agent systems governed by unknown, nonlinear dynamics. Most existing algorithms either assume certain parametric forms for the unknown dynamic…
For future human-autonomous vehicle (AV) interactions to be effective and smooth, human-aware systems that analyze and align human needs with automation decisions are essential. Achieving this requires systems that account for human…
Agent-Based Models (ABMs) are powerful tools for studying emergent properties in complex systems. In ABMs, agent behaviors are governed by local interactions and stochastic rules. However, these rules are, in general, non-differentiable,…
Agent-Based Models are very useful for simulation of physical or social processes, such as the spreading of a pandemic in a city. Such models proceed by specifying the behavior of individuals (agents) and their interactions, and…
Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…