Towards Principled Superhuman AI for Multiplayer Symmetric Games
- URL: http://arxiv.org/abs/2406.04201v1
- Date: Thu, 6 Jun 2024 15:59:17 GMT
- Title: Towards Principled Superhuman AI for Multiplayer Symmetric Games
- Authors: Jiawei Ge, Yuanhao Wang, Wenzhe Li, Chi Jin,
- Abstract summary: Multiplayer games, when the number of players exceeds two, present unique challenges.
These challenges arise from the non-uniqueness of equilibria and the risk of agents performing highly suboptimally.
This paper takes the first step towards solving these challenges by provably addressing both questions in multiplayer symmetric normal-form games.
- Score: 21.168085154982712
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multiplayer games, when the number of players exceeds two, present unique challenges that fundamentally distinguish them from the extensively studied two-player zero-sum games. These challenges arise from the non-uniqueness of equilibria and the risk of agents performing highly suboptimally when adopting equilibrium strategies. While a line of recent works developed learning systems successfully achieving human-level or even superhuman performance in popular multiplayer games such as Mahjong, Poker, and Diplomacy, two critical questions remain unaddressed: (1) What is the correct solution concept that AI agents should find? and (2) What is the general algorithmic framework that provably solves all games within this class? This paper takes the first step towards solving these unique challenges of multiplayer games by provably addressing both questions in multiplayer symmetric normal-form games. We also demonstrate that many meta-algorithms developed in prior practical systems for multiplayer games can fail to achieve even the basic goal of obtaining agent's equal share of the total reward.
Related papers
- Imperfect-Recall Games: Equilibrium Concepts and Their Complexity [74.01381499760288]
We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before.
In the framework of extensive-form games with imperfect recall, we analyze the computational complexities of finding equilibria in multiplayer settings.
arXiv Detail & Related papers (2024-06-23T00:27:28Z) - Leading the Pack: N-player Opponent Shaping [52.682734939786464]
We extend Opponent Shaping (OS) methods to environments involving multiple co-players and multiple shaping agents.
We find that when playing with a large number of co-players, OS methods' relative performance reduces, suggesting that in the limit OS methods may not perform well.
arXiv Detail & Related papers (2023-12-19T20:01:42Z) - TiZero: Mastering Multi-Agent Football with Curriculum Learning and
Self-Play [19.98100026335148]
TiZero is a self-evolving, multi-agent system that learns from scratch.
It outperforms previous systems by a large margin on the Google Research Football environment.
arXiv Detail & Related papers (2023-02-15T08:19:18Z) - Teamwork under extreme uncertainty: AI for Pokemon ranks 33rd in the
world [0.0]
This paper describes the mechanics of the game and we perform a game analysis.
We propose unique AI algorithms based on our understanding that the two biggest challenges in the game are keeping a balanced team and dealing with three sources of uncertainty.
Our AI agent performed significantly better than all previous attempts and peaked at the 33rd place in the world, in one of the most popular battle formats, while running on only 4 single socket servers.
arXiv Detail & Related papers (2022-12-27T01:52:52Z) - A Survey of Decision Making in Adversarial Games [8.489977267389934]
In many practical applications, such as poker, chess, evader pursuing, drug interdiction, coast guard, cyber-security, and national defense, players often have apparently adversarial stances.
This paper provides a systematic survey on three main game models widely employed in adversarial games.
arXiv Detail & Related papers (2022-07-16T16:04:01Z) - No-Regret Learning in Time-Varying Zero-Sum Games [99.86860277006318]
Learning from repeated play in a fixed zero-sum game is a classic problem in game theory and online learning.
We develop a single parameter-free algorithm that simultaneously enjoys favorable guarantees under three performance measures.
Our algorithm is based on a two-layer structure with a meta-algorithm learning over a group of black-box base-learners satisfying a certain property.
arXiv Detail & Related papers (2022-01-30T06:10:04Z) - Discovering Multi-Agent Auto-Curricula in Two-Player Zero-Sum Games [31.97631243571394]
We introduce a framework, LMAC, that automates the discovery of the update rule without explicit human design.
Surprisingly, even without human design, the discovered MARL algorithms achieve competitive or even better performance.
We show that LMAC is able to generalise from small games to large games, for example training on Kuhn Poker and outperforming PSRO.
arXiv Detail & Related papers (2021-06-04T22:30:25Z) - Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes)
We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play.
Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
arXiv Detail & Related papers (2021-04-17T20:33:24Z) - Suphx: Mastering Mahjong with Deep Reinforcement Learning [114.68233321904623]
We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques.
Suphx has demonstrated stronger performance than most top human players in terms of stable rank.
This is the first time that a computer program outperforms most top human players in Mahjong.
arXiv Detail & Related papers (2020-03-30T16:18:16Z) - Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games [22.38765498549914]
We argue that a systematic study of many-player zero-sum games is a crucial element of artificial intelligence research.
Using symmetric zero-sum matrix games, we demonstrate formally that alliance formation may be seen as a social dilemma.
We show how reinforcement learning may be augmented with a peer-to-peer contract mechanism to discover and enforce alliances.
arXiv Detail & Related papers (2020-02-27T10:32:31Z) - Neural MMO v1.3: A Massively Multiagent Game Environment for Training
and Evaluating Neural Networks [48.5733173329785]
We present Neural MMO, a massively multiagent game environment inspired by MMOs.
We discuss our progress on two more general challenges in multiagent systems engineering for AI research: distributed infrastructure and game IO.
arXiv Detail & Related papers (2020-01-31T18:50:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.