mlsanityData to 7 Oct 2026

Safe Exploitative Play with Untrusted Type Beliefs

arXiv 2411.07679 ↗First posted 12 Nov 2024cs.LG cs.GTcited by 0

Not on the map. Why?

Abstract (arXiv)

The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types, each specifying a possible behavior for the other agents. The idea is to plan an agent's own actions with respect to those types which it believes are most likely to maximize the payoff. However, the type beliefs are often learned from past actions and likely to be incorrect. With this perspective in mind, we consider an agent in a game with type predictions of other components, and investigate the impact of incorrect beliefs to the agent's payoff. In particular, we formally define a tradeoff between risk and opportunity by comparing the payoff obtained against the optimal payoff, which is represented by a gap caused by trusting or distrusting the learned beliefs. Our main results characterize the tradeoff by establishing upper and lower bounds on the Pareto front for both normal-form and stochastic Bayesian games, with numerical results provided.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 57 references that are in the map. First posted on arXiv 12 Nov 2024.

Builds on

24 of 57 references.

References · 24

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  2. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  3. 2018Competitive caching with machine learned advicecited by 194
  4. 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 126
  5. 2020Online metric algorithms with untrusted predictionscited by 74
  6. 2019Near-Optimal Bounds for Online Caching with Machine Learned Advicecited by 73
  7. 2024Improving Online Algorithms via ML Predictionscited by 65
  8. 2015A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systemscited by 41
  9. 2021The best of both worlds: stochastic and adversarial episodic MDPs with unknown transitioncited by 40
  10. 2015Belief and Truth in Hypothesised Behaviourscited by 19
  11. 2022Parsimonious Learning-Augmented Cachingcited by 19
  12. 2022Chasing Convex Bodies and Functions with Black-Box Advicecited by 19
12 more
  1. 2023Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Gamecited by 18
  2. 2022Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearitycited by 16
  3. 2021Robustness and Consistency in Linear Quadratic Control with Untrusted Predictionscited by 14
  4. 2023On the Convergence of No-Regret Learning Dynamics in Time-Varying Gamescited by 14
  5. 2021Can Q-Learning be Improved with Advice?cited by 13
  6. 2022Better Best of Both Worlds Bounds for Bandits with Switching Costscited by 13
  7. 2023Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictionscited by 8
  8. 2020Learning-Based Predictive Control via Real-Time Aggregate Flexibilitycited by 7
  9. 2022Computing Bayes Nash Equilibrium Strategies in Auction Games via Simultaneous Online Dual Averagingcited by 6
  10. 2023Robust Learning for Smoothed Online Convex Optimization with Feedback Delaycited by 3
  11. 2023Anytime-Competitive Reinforcement Learning with Policy Priorcited by 1
  12. 2023Out-of-Distribution-Aware Electric Vehicle Chargingcited by 1

Built on by

Not cited yet.