A data-driven discretized CS:GO simulation environment to facilitate strategic multi-agent planning research

2025-09-08

AI Summary

This work addresses the challenge of simultaneously achieving strategic abstraction and environmental fidelity in multi-agent simulation. We propose DECOY, a data-driven discrete simulator that replaces low-level physical modeling (e.g., aiming, shooting) with a waypoint-based state-action discretization framework. A neural predictive model is trained directly on professional CS:GO match data to learn mappings between high-level movement decisions and tactical outcomes. Our key contribution is the first demonstration that high-fidelity combat replays—statistically indistinguishable from original gameplay at the strategic level—can be reconstructed solely from coarse-grained mobility decisions, without simulating micro-actions. Evaluation shows an average trajectory similarity exceeding 92% against ground-truth game traces. DECOY is open-sourced, providing an efficient, interpretable, and scalable simulation platform for long-horizon multi-agent planning research in 3D environments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Modern simulation environments for complex multi-agent interactions must balance high-fidelity detail with computational efficiency. We present DECOY, a novel multi-agent simulator that abstracts strategic, long-horizon planning in 3D terrains into high-level discretized simulation while preserving low-level environmental fidelity. Using Counter-Strike: Global Offensive (CS:GO) as a testbed, our framework accurately simulates gameplay using only movement decisions as tactical positioning -- without explicitly modeling low-level mechanics such as aiming and shooting. Central to our approach is a waypoint system that simplifies and discretizes continuous states and actions, paired with neural predictive and generative models trained on real CS:GO tournament data to reconstruct event outcomes. Extensive evaluations show that replays generated from human data in DECOY closely match those observed in the original game. Our publicly available simulation environment provides a valuable tool for advancing research in strategic multi-agent planning and behavior generation.

Problem

• Simulating strategic multi-agent planning in 3D environments
• Balancing high-fidelity detail with computational efficiency
• Discretizing continuous states and actions for CS:GO gameplay

Innovation

• Discretized simulation with waypoint system
• Neural models trained on tournament data
• High-level planning without low-level mechanics