Výsledky vyhledávání - "Fang, Zhemei"

Report

Preference-CFR$\:$ Beyond Nash Equilibrium for Better Game Strategies

Autor: Ju, Qi, Tellier, Thomas, Sun, Meng, Fang, Zhemei, Luo, Yunfeng

Recent advancements in artificial intelligence (AI) have leveraged large-scale games as benchmarks to gauge progress, with AI now frequently outperforming human capabilities. Traditionally, this success has largely relied on solving Nash equilibrium

Externí odkaz: http://arxiv.org/abs/2411.01217

Zobrazit plný text záznamu

Report

ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models

Autor: Ju, Qi, Hei, Falin, Fang, Zhemei, Luo, Yunfeng

Reinforcement Learning (RL) is highly dependent on the meticulous design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term RL (LTRL) challenges is formidable. Consequently, RL agents are predominantl

Externí odkaz: http://arxiv.org/abs/2409.03301

Zobrazit plný text záznamu

Report

Beyond Nash Equilibrium: Achieving Bayesian Perfect Equilibrium with Belief Update Fictitious Play

Autor: Ju, Qi, Fang, Zhemei, Luo, Yunfeng

In the domain of machine learning and game theory, the quest for Nash Equilibrium (NE) in extensive-form games with incomplete information is challenging yet crucial for enhancing AI's decision-making support under varied scenarios. Traditional Count

Externí odkaz: http://arxiv.org/abs/2409.02706

Zobrazit plný text záznamu

Report

From First-Order to Second-Order Rationality: Advancing Game Convergence with Dynamic Weighted Fictitious Play

Autor: Ju, Qi, Hei, Falin, Liu, Yuxuan, Fang, Zhemei, Luo, Yunfeng

Constructing effective algorithms to converge to Nash Equilibrium (NE) is an important problem in algorithmic game theory. Prior research generally posits that the upper bound on the convergence rate for games is $O\left(T^{-1/2}\right)$. This paper

Externí odkaz: http://arxiv.org/abs/2402.12164

Zobrazit plný text záznamu

Report

Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play

Autor: Qi, Ju, Hei, Falin, Feng, Ting, Yi, Dengbing, Fang, Zhemei, Luo, Yunfeng

Counterfactual Regret Minimization (CFR) and its variants are widely recognized as effective algorithms for solving extensive-form imperfect information games. Recently, many improvements have been focused on enhancing the convergence speed of the CF

Externí odkaz: http://arxiv.org/abs/2309.03084

Zobrazit plný text záznamu