Abstract
Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating strategic command selection from learned unit control allows different strategies to be selected for different opponents while reusing the same execution policy. This requires an executor that can follow different commands and measurable criteria for assessing whether it does so. We introduce a constrained command-conditioned Proximal Policy Optimization (PPO) policy, the executor, for MicroRTS, a real-time strategy environment. Discrete commands specify strategic objectives and behavioral requirements for economy, army composition, military posture, and worker policy over multiple environment steps; the executor determines the unit-level actions used to fulfill them. A Thompson-sampling bandit acts as the strategist, selecting command tuples from an estimate of the opponent's strategy built from in-game observations rather than opponent identity. In a controlled comparison with a flat PPO baseline trained with the same architecture, budget, curriculum and self-play league, the strategist-executor system wins significantly more often against three of the four strongest opponents on a training map, including the two strongest held-out ones (0.55 to 0.97 and 0.01 to 0.34), with no significant difference against the others.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Leenders, N., Lindelauf, R., van Oijen, J., & Cule, B. (2026). Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games. https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games
MLA 9
Leenders, Nick, et al. "Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games." https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games.
Chicago (author–date)
Leenders, Nick, Roy Lindelauf, Joost van Oijen, and Boris Cule. 2026. "Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games." https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games.
Harvard
Leenders, N., Lindelauf, R., van Oijen, J. and Cule, B. (2026) 'Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games', Available at: https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games.
Vancouver
Leenders N, Lindelauf R, van Oijen J, Cule B. Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games. https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games
IEEE
N. Leenders, R. Lindelauf, J. van Oijen, and B. Cule, "Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games," https://omanscience.com/en/articles/constrained-command-conditioned-reinforcement-learning-with-bandit-strategy-selection-in-real-time-strategy-games.