Research map / Multi-agent systems and games / Human-AI and goal-conditioned
StarCraft Motion: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces StarCraft Motion, a large-scale dataset of human StarCraft gameplay for agent simulation in adversarial, partially observable multi-agent settings.
Problem
Agent simulation benchmarks focus on structured domains like autonomous driving, leaving adversarial and partially observable multi-agent behavior underexplored.
Approach
A large-scale dataset built from human StarCraft gameplay to model future behavior of interacting agents under adversarial and partial observability.
Experimental setup
Datasets: StarCraft human gameplay data
Closest papers by meaning
- FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.86)
- Learning Strategy Representation for Imitation Learning in Multi-Agent Games (AAAI 2025 · similarity 0.85)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.85)
- Opponent Modeling based on Subgoal Inference (NeurIPS 2024 · similarity 0.85)
- An Open-Ended Learning Framework for Opponent Modeling (AAAI 2025 · similarity 0.85)
- Generalized Intention Modeling in Multi-Agent Reinforcement Learning (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.