paper-with-me

홈 › Papers

Neural Population Learning beyond Symmetric Zero-sum Games

2024-01-10 · SiQi Liu, Luke Marris, Marc Lanctot, Georgios Piliouras, Joel Z. Leibo, Nicolas Heess

We study computationally efficient methods for finding equilibria in n-player general-sum games, specifically ones that afford complex visuomotor skills. We show how existing methods would struggle in this setting, either computationally or in theory. We then introduce NeuPL-JPSRO, a neural population learning algorithm that benefits from transfer learning of skills and converges to a Coarse Correlated Equilibrium (CCE) of the game. We show empirical convergence in a suite of OpenSpiel games, validated rigorously by exact game solvers. We then deploy NeuPL-JPSRO to complex domains, where our approach enables adaptive coordination in a MuJoCo control domain and skill transfer in capture-the-flag. Our work shows that equilibrium convergent population learning can be implemented at scale and in generality, paving the way towards solving real-world games between heterogeneous players with mixed motives.

📄 PDF Abstract BibTeX arXiv:2401.05133

Code (0)

등록된 구현이 없습니다.

Tasks

MuJoCoTransfer Learning

Similar Papers 제목 키워드 기반

MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games

2024-05-01 · Anran Hu, Junzi Zhang

Reinforcement learning for multi-agent games has attracted lots of attention recently. However, given the challenge of solving Nash equilibria for large population games, existing works with guaranteed polynomial complex…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Open-ended Learning in Symmetric Zero-sum Games

2019-01-23 · David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech M. Czarnecki 외

Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences…

Structural symmetry in evolutionary games

2015-09-12

In evolutionary game theory, an important measure of a mutant trait (strategy) is its ability to invade and take over an otherwise-monomorphic population. Typically, one quantifies the success of a mutant strategy via th…

Real World Games Look Like Spinning Tops

2020-04-20 · NeurIPS 2020 12 · Wojciech Marian Czarnecki, Gauthier Gidel, Brendan Tracey, Karl Tuyls 외

This paper investigates the geometrical properties of real world games (e.g. Tic-Tac-Toe, Go, StarCraft II). We hypothesise that their geometrical structure resemble a spinning top, with the upright axis representing tra…

ClusteringStarcraftStarcraft II

Dynamical stability of evolutionarily stable strategy in asymmetric games

2024-09-28 · Vikash Kumar Dubey, Suman Chakraborty, Arunava Patra, Sagar Chakraborty

Evolutionarily stable strategy (ESS) is the defining concept of evolutionary game theory. It has a fairly unanimously accepted definition for the case of symmetric games which are played in a homogeneous population where…