Evolution of Societies via Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bouteiller, Yann, Soma, Karthik, Beltrame, Giovanni
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910919891615744
author Bouteiller, Yann
Soma, Karthik
Beltrame, Giovanni
author_facet Bouteiller, Yann
Soma, Karthik
Beltrame, Giovanni
contents 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 populations evolve under both naive and advanced MARL rules, including compelling ways in which Opponent-Learning Awareness affects social evolution.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17466
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evolution of Societies via Reinforcement Learning
Bouteiller, Yann
Soma, Karthik
Beltrame, Giovanni
Machine Learning
Computer Science and Game Theory
Multiagent Systems
Populations and Evolution
General Finance
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 populations evolve under both naive and advanced MARL rules, including compelling ways in which Opponent-Learning Awareness affects social evolution.
title Evolution of Societies via Reinforcement Learning
topic Machine Learning
Computer Science and Game Theory
Multiagent Systems
Populations and Evolution
General Finance
url https://arxiv.org/abs/2410.17466