.png){kind=icon}
.png){kind=icon}
Return
Opponent aware reinforcement learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.ejor.2026.08.031.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
<ul class="list">
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e774">
Introduce Threatened MDPs to support RL agents facing adversaries.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e779">
Integrate 3 opponent modeling principles into Q-learning from a single-agent view.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e784">
Propose a level-k thinking scheme with linear-in-k time and space complexity.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e789">
Prove convergence of the augmented Q-learning rule via a contraction mapping.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e794">
Empirically show robustness to opponent misspecification on security RL benchmarks.
</div></span></li>
</ul>
Keywords:
Artificial intelligence
Multi-agent reinforcement learning
Game theory
Level-k thinking
Journal
IF:
6
Papers:
2.2W
Citations:
6.4W
View more organizations