Cooperative Artificial Intelligence

Abstract

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We argue that there is a need for research on the intersection between game theory and artificial intelligence, with the goal of achieving cooperative artificial intelligence that can navigate social dilemmas well. We consider the problem of how an external agent can promote cooperation between artificial learners by distributing additional rewards and punishments based on observing the actions of the learners. We propose a rule for automatically learning how to create the right incentives by considering the anticipated parameter updates of each agent. Using this learning rule leads to cooperation with high social welfare in matrix games in which the agents would otherwise learn to defect with high probability. We show that the resulting cooperative outcome is stab

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybaumann2022cooperative

Related papers

• Adversarial Attacks In Cooperative AI (2021)0.00
• Emergent Cooperation Through Mutual Information Maximization (2020)0.00
• Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
• Evolving Intrinsic Motivations For Altruistic Behavior (2018)2.26
• Reciprocal Reward Influence Encourages Cooperation From Self-interested Agents (2024)1.91
• Cooperation And Reputation Dynamics With Reinforcement Learning (2021)3.58
• Achieving Collective Welfare In Multi-agent Reinforcement Learning Via Suggestion Sharing (2024)0.00
• Improved Cooperation By Balancing Exploration And Exploitation In Intertemporal Social Dilemma Tasks (2021)0.00