Learning to act in a multiagent environment is a challenging problem. Optimal behavior for one agent depends upon the behavior of the other agents, which are learning as well …
AL Thomaz, C Breazeal - 5th Intl. Conf. on Development and …, 2006 - robots.media.mit.edu
In this paper we advocate a paradigm of socially guided machine learning, designing agents that take better advantage of the situated aspects of learning. We augmented a standard …
Y Zang, J He, K Li, H Fu, Q Fu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Grouping is ubiquitous in natural systems and is essential for promoting efficiency in team coordination. This paper proposes a novel formulation of Group-oriented Multi-Agent …
This work considers the problem of learning cooperative policies in complex, partially observable domains without explicit communication. We extend three classes of single …
FL Da Silva, AHR Costa - Journal of Artificial Intelligence Research, 2019 - jair.org
Multiagent Reinforcement Learning (RL) solves complex tasks that require coordination with other agents through autonomous exploration of the environment. However, learning a …
N Haber, D Mrowca, S Wang… - Advances in neural …, 2018 - proceedings.neurips.cc
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 …
Seamlessly interacting with humans or robots is hard because these agents are non- stationary. They update their policy in response to the ego agent's behavior, and the ego …
Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a …
The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors …