A model-based solution to the offline multi-agent reinforcement learning coordination problem
Training multiple agents to coordinate is an essential problem with applications in robotics,
game theory, economics, and social sciences. However, most existing Multi-Agent …
game theory, economics, and social sciences. However, most existing Multi-Agent …
Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication
In this paper, we investigate whether artificial agents can develop a shared language in an
ecological setting where communication relies on a sensory-motor channel. To this end, we …
ecological setting where communication relies on a sensory-motor channel. To this end, we …
[PDF][PDF] Towards Social Autotelic Artificial Agents
T KARCH - 2023 - theses.hal.science
2 Background: Standard AI Paradigms 11 2.1 Reinforcement Learning............................ 11
2.2 Imitation Learning............................... 16 2.3 Muli-Goal Reinforcement …
2.2 Imitation Learning............................... 16 2.3 Muli-Goal Reinforcement …
[图书][B] Coordination in Cooperative Multi-Agent Learning
P Barde - 2023 - search.proquest.com
Exploring the process by which autonomous agents coordinate represents a pivotal
advancement toward emulating populations, which encompasses diverse applications in …
advancement toward emulating populations, which encompasses diverse applications in …
Agents artificiels autotelic et sociaux: formation et exploitation de conventions culturelles chez les agents artificiels autonomes incarnés
T Karch - 2023 - theses.hal.science
L'un des objectifs fondamentaux de l'Intelligence Artificielle (IA) est de concevoir des agents
autonomes incarnés capables d'évoluer dans divers environnements, d'accomplir une …
autonomes incarnés capables d'évoluer dans divers environnements, d'accomplir une …
Emergence of shared sensory-motor graphical language from visual input
The framework of Language Games studies the emergence of languages in populations of
agents. Recent contributions relying on deep learning methods focused on agents …
agents. Recent contributions relying on deep learning methods focused on agents …