Characterizing Robustness of Strategies to Novelty in Zero-Sum Open Worlds

2026-02-15

AI Summary

This study investigates the robustness of fixed-policy agents in open-world settings when confronted with environmental novelty, such as changes in game rules or payoff structures. Framed within a two-player zero-sum game context, the work systematically perturbs the reward mechanisms of the Iterated Prisoner’s Dilemma (IPD) and the rule set of Texas Hold’em poker. It introduces two quantitative metrics—individual strategy robustness and global perturbation magnitude—to evaluate performance degradation across 30 IPD agents and 10 poker agents under diverse perturbations. The experiments identify specific types of novelty that critically destabilize agent strategies, offering both theoretical insights and empirical evidence to guide the development of more generalizable adversarial intelligent systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Game Theory and Economic Paradigms: Adversarial Learning
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In open-world environments, artificial agents must often contend with novel conditions that deviate from their training or design assumptions. This paper studies the robustness of fixed-strategy agents to such novelty within the setting of two-player zero-sum games. We present a general framework for characterizing the impact of environmental novelties, such as changes in payoff structure or action constraints, on agent performance in two distinct domains: Iterated Prisoner's Dilemma (IPD) and heads-up Texas Hold'em Poker. Novelty is operationalized as a perturbation of the game's rules or scoring mechanics, while agent behavior remains fixed. To measure the effects, we introduce two metrics: per-agent robustness, quantifying the relative performance shift of each strategy across novelties, and global impact, summarizing the population-wide disruption caused by a novelty. Our experiments, comprising 30 IPD agents across 20 payoff matrix novelties and 10 Poker agents across 5 rule-based novelties, reveal systematic patterns in robustness and highlight certain novelties that induce severe destabilization. The results offer insights into agent generalizability under perturbation and provide a quantitative basis for designing safer and more resilient autonomous systems in adversarial and dynamic environments.

Problem

• robustness
• novelty
• zero-sum games
• open-world environments
• agent generalizability

Innovation

• robustness
• novelty
• zero-sum games
• open-world
• strategy evaluation