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

TL;DR

This paper introduces a framework to evaluate how fixed strategies in zero-sum open-world games respond to environmental novelties, revealing patterns of robustness and destabilization in two key domains.

Contribution

It provides a novel general framework and metrics for analyzing the robustness of fixed strategies to environmental changes in zero-sum games.

Findings

Certain novelties cause significant destabilization of strategies.

Robustness varies systematically across different strategies and novelties.

Insights into designing more resilient agents in dynamic environments.

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.