mlsanityData to 7 Oct 2026

How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agents

arXiv 2112.07640 ↗First posted 14 Dec 2021cs.GT cs.AI cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. Motivated by such applications, this paper is dedicated to fundamental modeling and analysis of the strategic situations that the users of automated learning agents are facing. We consider strategic settings where several users engage in a repeated online interaction, assisted by regret-minimizing learning agents that repeatedly play a "game" on their behalf. We propose to view the outcomes of the agents' dynamics as inducing a "meta-game" between the users. Our main focus is on whether users can benefit in this meta-game from "manipulating" their own agents by misreporting their parameters to them. We define a general framework to model and analyze these strategic interactions between users of learning agents for general games and analyze the equilibria induced between the users in three classes of games. We show that, generally, users have incentives to misreport their parameters to their own agents, and that such strategic user behavior can lead to very different outcomes than those anticipated by standard analysis.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 28 of its 105 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

28 of 105 references.

References · 28

  1. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  2. 2015Strategic Classificationcited by 256
  3. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
  4. 2015Fast Convergence of Regularized Learning in Gamescited by 149
  5. 2017Strategic Classification from Revealed Preferencescited by 126
  6. 2017Cycles in adversarial regularized learningcited by 122
  7. 2018Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimizationcited by 97
  8. 2021Near-Optimal No-Regret Learning in General Gamescited by 85
  9. 2021Strategic Classification in the Darkcited by 66
  10. 2021Strategic Classification Made Practicalcited by 58
  11. 2020Hedging in games: Faster convergence of external and swap regretscited by 57
  12. 2019Strategizing against No-regret Learnerscited by 48
16 more
  1. 2020Maximizing Welfare with Incentive-Aware Evaluation Mechanismscited by 46
  2. 2017Selling to a No-Regret Buyercited by 43
  3. 2018A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providerscited by 33
  4. 2014Optimum Statistical Estimation with Strategic Data Sourcescited by 28
  5. 2019Learning Reciprocity in Complex Sequential Social Dilemmascited by 24
  6. 2015Econometrics for Learning Agentscited by 23
  7. 2015Learning in Auctions: Regret is Hard, Envy is Easycited by 23
  8. 2021Auctions Between Regret-Minimizing Agentscited by 22
  9. 2021Robust Auction Design in the Auto-bidding Worldcited by 21
  10. 2021Towards Efficient Auctions in an Auto-bidding Worldcited by 19
  11. 2020Bid Prediction in Repeated Auctions with Learningcited by 14
  12. 2020Optimally Deceiving a Learning Leader in Stackelberg Gamescited by 11
  13. 2019Imitative Follower Deception in Stackelberg Gamescited by 9
  14. 2019Manipulating a Learning Defender and Ways to Counteractcited by 8
  15. 2020Optimal Collaterals in Multi-Enterprise Investment Networkscited by 4
  16. 2021Stochastic Multiplicative Weights Updates in Zero-Sum Gamescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 9; 2025: 4; 2026: 1.

17 papers.

Sort:

By area:

  1. 2024Contracting with a Learning Agentcited by 22
  2. 2022Learning When to Advise Human Decision Makerscited by 18
  3. 2025Security of Internet of Agents: Attacks and Countermeasurescited by 17
  4. 2024Strategizing against No-Regret Learners in First-Price Auctionscited by 8
  5. 2023Cooperative AI via Decentralized Commitment Devicescited by 7
  6. 2024Strategically-Robust Learning Algorithms for Bidding in First-Price Auctionscited by 7
  7. 2024Maximizing utility in multi-agent environments by anticipating the behavior of other learnerscited by 7
  8. 2024Impact of Decentralized Learning on Player Utilities in Stackelberg Gamescited by 5
  9. 2024Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactionscited by 5
  10. 2023Learning to Manipulate a Commitment Optimizercited by 3
  11. 2024Games with Payments between Learning Agentscited by 3
  12. 2024Learning to Play Against Unknown Opponentscited by 3
5 more
  1. 2024Randomized Truthful Auctions with Learning Agentscited by 1
  2. 2025Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learnerscited by 1
  3. 2025Best of Both Worlds: Regret Minimization versus Minimax Playcited by 1
  4. 2026From No-Regret to Strategically Robust Learning in Repeated Auctionscited by 1
  5. 2025Learning in Strategic Queuing Systems with Small Bufferscited by 0