A utility-based analysis of equilibria in multi-objective normal-form games

@article{Rdulescu2020AUA,
  title={A utility-based analysis of equilibria in multi-objective normal-form games},
  author={Roxana Rădulescu and P. Mannion and Yijie Zhang and Diederik M. Roijers and A. Now{\'e}},
  journal={The Knowledge Engineering Review},
  year={2020},
  volume={35}
}
Abstract In multi-objective multi-agent systems (MOMASs), agents explicitly consider the possible trade-offs between conflicting objective functions. We argue that compromises between competing objectives in MOMAS should be analyzed on the basis of the utility that these compromises have for the users of a system, where an agent’s utility function maps their payoff vectors to scalar utility values. This utility-based approach naturally leads to two different optimization criteria for agents in… Expand
7 Citations
A Practical Guide to Multi-Objective Reinforcement Learning and Planning
  • PDF
Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games
  • 1
  • PDF
Exploring the Impact of Tunable Agents in Sequential Social Dilemmas
  • 1
  • PDF
An interpretable semi-supervised classifier using two different strategies for amended self-labeling
  • 2
  • PDF
Special issue on adaptive and learning agents 2019
  • PDF

References

SHOWING 1-10 OF 54 REFERENCES
Equilibria in Multi-Objective Games: a Utility-Based Perspective
  • 7
  • PDF
An Evolutionary Game Theoretic Analysis of Difference Evaluation Functions
  • 12
  • PDF
Quality Assessment of MORL Algorithms: A Utility-Based Approach
  • 14
  • PDF
Multi-objective decision-theoretic planning
  • 12
  • PDF
Multi-criteria Coalition Formation Games
  • 6
  • PDF
A Theoretical and Empirical Analysis of Reward Transformations in Multi-Objective Stochastic Games
  • 9
  • Highly Influential
Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information
  • 9
  • PDF
Multiple criteria games — Theory and applications
  • 21
Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II
  • 15
  • PDF
...
1
2
3
4
5
...