Evolving Intrinsic Motivations For Altruistic Behavior

Abstract

Multi-agent cooperation is an important feature of the natural world. Many tasks involve individual incentives that are misaligned with the common good, yet a wide range of organisms from bacteria to insects and humans are able to overcome their differences and collaborate. Therefore, the emergence of cooperative behavior amongst self-interested individuals is an important question for the fields of multi-agent reinforcement learning (MARL) and evolutionary theory. Here, we study a particular class of multi-agent problems called intertemporal social dilemmas (ISDs), where the conflict between the individual and the group is particularly sharp. By combining MARL with appropriately structured natural selection, we demonstrate that individual inductive biases for cooperation can be learned in a model-free way. To achieve this, we introduce an innovative modular architecture for deep reinforcement learning agents which supports multi-level selection. We present results in two challenging e

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keywang2018evolving

Related papers

• Improved Cooperation By Balancing Exploration And Exploitation In Intertemporal Social Dilemma Tasks (2021)0.00
• Intrinsic Fluctuations Of Reinforcement Learning Promote Cooperation (2022)9.23
• Inclusive Fitness As A Key Step Towards More Advanced Social Behaviors In Multi-agent Reinforcement Learning Settings (2025)0.00
• Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
• Understanding The World To Solve Social Dilemmas Using Multi-agent Reinforcement Learning (2023)0.00
• Evolutionary Multi-agent Reinforcement Learning In Group Social Dilemmas (2024)0.00