DeepAI AI Chat
Log In Sign Up

Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-agent Reinforcement Learning

by   William Long, et al.

Cooperation is a phenomenon that has been widely studied across many different disciplines. In the field of computer science, the modularity and robustness of multi-agent systems offer significant practical advantages over individual machines. At the same time, agents using standard reinforcement learning algorithms often fail to achieve long-term, cooperative strategies in unstable environments when there are short-term incentives to defect. Political philosophy, on the other hand, studies the evolution of cooperation in humans who face similar incentives to act individualistically, but nevertheless succeed in forming societies. Thomas Hobbes in Leviathan provides the classic analysis of the transition from a pre-social State of Nature, where consistent defection results in a constant state of war, to stable political community through the institution of an absolute Sovereign. This thesis argues that Hobbes's natural and moral philosophy are strikingly applicable to artificially intelligent agents and aims to show that his political solutions are experimentally successful in producing cooperation among modified Q-Learning agents. Cooperative play is achieved in a novel Sequential Social Dilemma called the Civilization Game, which models the State of Nature by introducing the Hobbesian mechanisms of opponent learning awareness and majoritarian voting, leading to the establishment of a Sovereign.


Intrinsic fluctuations of reinforcement learning promote cooperation

In this work, we ask for and answer what makes classical reinforcement l...

Evolving intrinsic motivations for altruistic behavior

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

Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments

Recent reinforcement learning studies extensively explore the interplay ...

Multiagent Cooperation and Competition with Deep Reinforcement Learning

Multiagent systems appear in most social, economical, and political situ...

Cooperative Multi-Agent Search on Endogenously-Changing Fitness Landscapes

We use a multi-agent system to model how agents (representing firms) may...

Evolution of Cooperative Hunting in Artificial Multi-layered Societies

The complexity of cooperative behavior is a crucial issue in multiagent-...