Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems

by   Nayana Dasgupta, et al.

The problem of cooperation is of fundamental importance for human societies, with examples ranging from navigating road junctions to negotiating climate treaties. As the use of AI becomes more pervasive within society, the need for socially intelligent agents that are able to navigate these complex dilemmas is becoming increasingly evident. Direct punishment is an ubiquitous social mechanism that has been shown to benefit the emergence of cooperation within the natural world, however no prior work has investigated its impact on populations of learning agents. Moreover, although the use of all forms of punishment in the natural world is strongly coupled with partner selection and reputation, no existing work has provided a holistic analysis of their combination within multi-agent systems. In this paper, we present a comprehensive analysis of the behaviors and learning dynamics associated with direct punishment in multi-agent reinforcement learning systems and how this compares to third-party punishment, when both forms of punishment are combined with other social mechanisms such as partner selection and reputation. We provide an extensive and systematic evaluation of the impact of these key mechanisms on the emergence of cooperation. Finally, we discuss the implications of the use of these mechanisms in the design of cooperative AI systems.


page 1

page 2

page 3

page 4


Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning

Social dilemmas are situations where groups of individuals can benefit f...

Evolving intrinsic motivations for altruistic behavior

Multi-agent cooperation is an important feature of the natural world. Ma...

Modelling Cooperation in Network Games with Spatio-Temporal Complexity

The real world is awash with multi-agent problems that require collectiv...

Enabling Imitation-Based Cooperation in Dynamic Social Networks

The emergence of cooperation among self-interested agents has been a key...

Emergent Resource Exchange and Tolerated Theft Behavior using Multi-Agent Reinforcement Learning

For decades, the evolution of cooperation has piqued the interest of num...

Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research

Evolution has produced a multi-scale mosaic of interacting adaptive unit...

Causal Coupled Mechanisms: A Control Method with Cooperation and Competition for Complex System

Complex systems are ubiquitous in the real world and tend to have compli...

Please sign up or login with your details

Forgot password? Click here to reset