Opponent Modeling & Theory of Mind Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Predicting and shaping other agents requires modeling their beliefs and learning. This list covers opponent modeling, theory of mind, and learning-aware shaping from classic LOLA to modern Bayesian methods.

Opponent Modeling & Theory of Mind: 10 key papers

1. Learning with Opponent-Learning Awareness
   Foerster et al. arXiv 2017.
2. Opponent Modeling in Deep Reinforcement Learning
   He et al. arXiv 2016.
3. Machine Theory of Mind
   Rabinowitz et al. arXiv 2018.
4. Stable Opponent Shaping in Differentiable Games
   Letcher et al. arXiv 2018.
5. A Regularized Opponent Model with Maximum Entropy Objective
   Tian et al. arXiv 2019.
6. Learning Policy Representations in Multiagent Systems
   Grover et al. arXiv 2018.
7. Modeling Others using Oneself in Multi-Agent Reinforcement Learning
   Raileanu et al. arXiv 2018.
8. Bayesian Opponent Exploitation in Imperfect-Information Games
   Ganzfried and Sun. arXiv 2016.
9. Model-Free Opponent Shaping
   Lu et al. arXiv 2022.
10. Agent Modelling under Partial Observability for Deep Reinforcement Learning
    Papoudakis et al. arXiv 2020.

Related reading lists

• Self-Play & Population-Based Training
• Game Theory for Multi-Agent Systems
• Reward Learning & Reward Modeling
• Mean-Field Games & Mean-Field Control
• Bayesian Optimization & Global Optimization
• Multi-Agent Reinforcement Learning
• Transformers for Sequential Decision Making
• Fairness & Bias in ML