Evolution Of Societies Via Reinforcement Learning

Abstract

The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous populations and remain computationally intensive. We propose a methodology that enables simulating populations of Reinforcement Learning agents at evolutionary scale. More specifically, we derive a fast, parallelizable implementation of Policy Gradient (PG) and Opponent-Learning Awareness (LOLA), tailored for evolutionary simulations where agents undergo random pairwise interactions in stateless normal-form games. We demonstrate our approach by simulating the evolution of very large populations made of heterogeneous co-learning agents, under both naive and advanced learning strategies. In our experiments, 200,000 PG or LOLA agents evolve in the classic games of Hawk-Dove, Stag-Hunt, and Rock-Paper-Scissors. Each game provides distinct insights into how popu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybouteiller2024evolution

Related papers

• Evolutionary Population Curriculum For Scaling Multi-agent Reinforcement Learning (2020)0.00
• The Evolutionary Dynamics Of Independent Learning Agents In Population Games (2020)0.00
• Policyevolve: Evolving Programmatic Policies By Llms For Multi-player Games Via Population-based Training (2025)0.00
• Game Theory And Multi-agent Reinforcement Learning : From Nash Equilibria To Evolutionary Dynamics (2024)0.00
• Generative Evolutionary Meta-solver (GEMS): Scalable Surrogate-free Multi-agent Reinforcement Learning (2025)0.00
• Discovering Multiagent Learning Algorithms With Large Language Models (2026)2.05
• Evolutionary Multi-agent Reinforcement Learning In Group Social Dilemmas (2024)0.00
• Strategic Coordination For Evolving Multi-agent Systems: A Hierarchical Reinforcement And Collective Learning Approach (2025)0.00