Goto

Collaborating Authors

From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

#artificialintelligence

A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula,, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed.


From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

#artificialintelligence

A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula,, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed.


Preface

AAAI Conferences

Multiagent Systems (MAS) have become an important sub-field of AI, and several classical AI topics are now broadly studied in their MAS (i.e. Multiagent Planning (MAP) extends classical AI Planning to domains where several agents can plan and act together. Application areas of MAP include multi-robot environments, cooperating Internet agents, logistics, manufacturing, military tasks etc. While related MAS disciplines (e.g. Distributed Constraint Satisfaction) have benefited from standardized problem specifications and benchmarks, existing work on MAP is still very heterogeneous.


Preface

AAAI Conferences

The main goals of the workshop are as follows: (1) Familiarize researchers from different areas with the vary- ing contributions on this problem. (2) Standardize terminology and develop a taxonomy for different variants. (3) Present the state-of-the-art and discuss open challenges. (4) Encourage collaboration between participants.


Self-Adjustable Autonomy in Multi-Agent Systems

AAAI Conferences

These questions have led to a wide variety of research disciplines. To make concrete these various research disciplines, several distributed architectures have been proposed. However, the use of these distributed architectures requires a very complex parametrization. This complexity is the result of the type of problem resolution which is founded on negotiation. Negotiation is one of the most important concept of the proposed architectures.