Are Equivariant Equilibrium Approximators Beneficial?
Not on the map. Why?
Abstract (arXiv)
Recently, remarkable progress has been made by approximating Nash equilibrium (NE), correlated equilibrium (CE), and coarse correlated equilibrium (CCE) through function approximation that trains a neural network to predict equilibria from game representations. Furthermore, equivariant architectures are widely adopted in designing such equilibrium approximators in normal-form games. In this paper, we theoretically characterize benefits and limitations of equivariant equilibrium approximators. For the benefits, we show that they enjoy better generalizability than general ones and can achieve better approximations when the payoff distribution is permutation-invariant. For the limitations, we discuss their drawbacks in terms of equilibrium selection and social welfare. Together, our results help to understand the role of equivariance in equilibrium approximators.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 27 Jan 2023.
Builds on
20 of 43 references.
References · 20
- 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
- 2021V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RLcited by 111
- 2021Provably Strict Generalisation Benefit for Equivariant Modelscited by 90
- 2019Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descentcited by 31
- 2020A Permutation-Equivariant Neural Network Architecture For Auction Designcited by 31
- 2022Optimal-er Auctions through Attentioncited by 26
- 2015Econometrics for Learning Agentscited by 23
- 2018What game are we playing? End-to-end learning in normal and extensive form gamescited by 22
- 2021Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solverscited by 21
- 2022A Context-Integrated Transformer-Based Neural Network for Auction Designcited by 19
- 2021On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Gamescited by 18
- 2021Contextual Games: Multi-Agent Learning with Side Informationcited by 11
8 more
- 2022Meta-Learning in Gamescited by 10
- 2022Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solverscited by 10
- 2020Learning Utilities and Equilibria in Non-Truthful Auctionscited by 8
- 2022Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Gamescited by 8
- 2022Benefits of Permutation-Equivariance in Auction Mechanismscited by 7
- 2022Exploitability Minimization in Games and Beyondcited by 6
- 2022A Polynomial-Time Algorithm for 1/3-Approximate Nash Equilibria in Bimatrix Gamescited by 5
- 2021Is Nash Equilibrium Approximator Learnable?cited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.