This is the pre-proceedings for the RLC 2026. You may expect minor changes.

Strategically-Linked Decisions in Long-Term Planning and Reinforcement Learning

By Alihan Hüyük, Jonas B Raedler, Leo Benac, and Finale Doshi-Velez

Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.

Will be presented at the Reinforcement Learning Conference (RLC), Montréal, Quebec, Canada, August 15–17, 2026.


Download:

Keywords: Strategic Decision-Making, Long-Term Planning, Reinforcement Learning,

Abstract:

Long-term planning, as in reinforcement learning (RL), is often hard to make interpretable to humans as it involves strategies: collections of actions that work toward a goal with potentially complex dependencies. In particular, some actions are taken at the expense of short-term benefit to enable future actions with even greater returns. In this paper, we quantify such dependencies between planned actions with strategic link scores: the drop in the likelihood of an earlier action under the constraint that a follow-up action is no longer available. We use strategic link scores to (i) explain black-box RL agents by identifying strategically-linked pairs among decisions they make, and (ii) improve the worst-case performance of decision support systems by distinguishing whether recommended actions can be adopted as standalone improvements, or whether they are strategically linked hence require a commitment to a broader strategy to be effective. We demonstrate these use cases with maze-solving and chess-playing examples as well as simulated healthcare, traffic, and crisis negotiation environments.


Citation Information:

Alihan Hüyük, Jonas B Raedler, Leo Benac, and Finale Doshi-Velez. "Strategically-Linked Decisions in Long-Term Planning and Reinforcement Learning." Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.

BibTeX:
@article{hyk2026strategicallylinked,
    title={Strategically-Linked Decisions in Long-Term Planning and Reinforcement Learning},
    author={Alihan Hüyük and Jonas B Raedler and Leo Benac and Finale Doshi-Velez},
    journal={Reinforcement Learning Journal},
    volume={7},
    pages={},
    year={2026}
}