相关论文: Causal Learning by a Robot with Semantic-Episodic …

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…

Humans interpret the world around them in terms of cause and effect and communicate their understanding of the world to each other in causal terms. These causal aspects of human cognition are thought to underlie humans' ability to…

Direct reciprocity is a mechanism for the evolution of cooperation in repeated social interactions. According to this literature, individuals naturally learn to adopt conditionally cooperative strategies if they have multiple encounters…

Determining a causal DAG (directed acyclic graph) for a problem under consideration, is a major roadblock when doing Judea Pearl's Causal Inference (CI) in Statistics. The same problem arises when doing CI in Artificial Intelligence (AI)…

We treat the problem of autonomous acquisition of manipulation skills where problem-solving strategies are initially available only for a narrow range of situations. We propose to extend the range of solvable situations by autonomous…

In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects…

This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional…

Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning.…

Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolve over time. We introduce the Causal Process Framework and…

In the fields of computation and neuroscience, much is still unknown about the underlying computations that enable key cognitive functions including learning, memory, abstraction and behavior. This paper proposes a mathematical and…

We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning.…

Recent advances in artificial intelligence reveal the limits of purely predictive systems and call for a shift toward causal and collaborative reasoning. Drawing inspiration from the revolution of Grothendieck in mathematics, we introduce…

Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. The paper…

Machine learning techniques have enabled robots to learn narrow, yet complex tasks and also perform broad, yet simple skills with a wide variety of objects. However, learning a model that can both perform complex tasks and generalize to…

Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.…

Deep learning's success in perception, natural language processing, etc. inspires hopes for advancements in autonomous robotics. However, real-world robotics face challenges like variability, high-dimensional state spaces, non-linear…

Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…

Using robots for automating tasks in environments shared with humans, such as warehouses, shopping centres, or hospitals, requires these robots to comprehend the fundamental physical interactions among nearby agents and objects.…

Imitation learning allows social robots to learn new skills from human teachers without substantial manual programming, but it is difficult for robotic imitation learning systems to generalize demonstrated skills as well as human learners…