Safe Exploitative Play with Untrusted Type Beliefs

Tongxin Li; Tinashe Handina; Shaolei Ren; Adam Wierman

NeurIPS · 2024

Safe Exploitative Play with Untrusted Type Beliefs

Tongxin Li, Tinashe Handina, Shaolei Ren, Adam Wierman

Advances in Neural Information Processing Systems

Read paper BibTeX

How much risk comes from exploiting a predicted opponent type?

The paper formalizes a risk and opportunity tradeoff for agents with uncertain beliefs about other players. Upper and lower bounds characterize the Pareto frontier in normal form and stochastic Bayesian games, with numerical illustrations of the tradeoff.

Research themes

Connections

Prediction errors become strategic risks

In strategic environments, advice quality affects both opportunity and risk. The Bayesian game and repeated game results expose limits on combining exploitation with protection against inaccurate beliefs.

Open questions

Accountable learning across agents

How should shared models balance efficiency, strategic risk, and equity?

Explore open directions

Cite this paper

Tongxin Li, Tinashe Handina, Shaolei Ren, Adam Wierman. Safe Exploitative Play with Untrusted Type Beliefs. Advances in Neural Information Processing Systems, 2024. https://papers.nips.cc/paper_files/paper/2024/hash/858e773f5c99a4186b548f3f531fb07e-Abstract-Conference.html

BibTeX

@inproceedings{tongxin-safe-play,
  title = {{Safe Exploitative Play with Untrusted Type Beliefs}},
  author = {Tongxin Li and Tinashe Handina and Shaolei Ren and Adam Wierman},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems},
  url = {https://papers.nips.cc/paper\_files/paper/2024/hash/858e773f5c99a4186b548f3f531fb07e-Abstract-Conference.html}
}

2026AISTATS

Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners

Tinashe Handina, Tongxin Li, Kishan Panaganti, Eric Mazumdar, Adam Wierman

A measure of advice quality connects simulators and payoff predictions to strategic performance. The paper establishes benefits of reliable advice for approximate Stackelberg play and limitations on simultaneously exploiting accurate advice and protecting against inaccurate advice.

Games and equity Predictions Paper