Emergent Dominance Hierarchies in Reinforcement Learning Agents
Modern Reinforcement Learning (RL) algorithms are able to outperform humans in a wide variety of tasks. Multi-agent reinforcement learning (MARL) settings present additional challenges, and successful cooperation in mixed-motive groups of agents depends on a delicate balancing act between individual and group objectives. Social conventions and norms, often inspired by human institutions, are used as tools for striking this balance. In this paper, we examine a fundamental, well-studied social convention that underlies cooperation in both animal and human societies: dominance hierarchies. We adapt the ethological theory of dominance hierarchies to artificial agents, borrowing the established terminology and definitions with as few amendments as possible. We demonstrate that populations of RL agents, operating without explicit programming or intrinsic rewards, can invent, learn, enforce, and transmit a dominance hierarchy to new populations. The dominance hierarchies that emerge have a similar structure to those studied in chickens, mice, fish, and other species.
Code (1)
Tasks
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective
Multi-agent self-organizing systems (MASOS) exhibit key characteristics including scalability, adaptability, flexibility, and robustness, which have contributed to their extensive application across various fields. Howev…
Multi-agent Reinforcement LearningUnderstanding Electro-communication and Electro-sensing in Weakly Electric Fish using Multi-Agent Deep Reinforcement Learning
Weakly electric fish, like Gnathonemus petersii, use a remarkable electrical modality for active sensing and communication, but studying their rich electrosensing and electrocommunication behavior and associated neural a…
Multi-agent Reinforcement LearningMultiagent Reinforcement Learning in Games with an Iterated Dominance Solution
Multiagent reinforcement learning (MARL) attempts to optimize policies of intelligent agents interacting in the same environment. However, it may fail to converge to a Nash equilibrium in some games. We study independen…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Multi-Agent Reinforcement Learning for Market Making: Competition without Collusion
Algorithmic collusion has emerged as a central question in AI: Will the interaction between different AI agents deployed in markets lead to collusion? More generally, understanding how emergent behavior, be it a cartel o…
Multi-agent Reinforcement LearningDrop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures
How much autonomy can multi-agent LLM systems sustain -- and what enables it? We present a 25,000-task computational experiment spanning 8 models, 4--256 agents, and 8 coordination protocols ranging from externally impos…