128 citations · 233 across the 14 of their papers we have counts for
14 papers
Is Elo Rating Reliable? A Study Under Model Misspecification
Shange Tang, Yuanhao Wang, Chi Jin
Elo rating, widely used for skill assessment across diverse domains ranging from competitive games to large language models, is often understood as an incremental update algorithm…
Is RLHF More Difficult than Standard RL?
Yuanhao Wang, Qinghua Liu, Chi Jin
Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward signals. Preferences arguab…
Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation
Yuanhao Wang, Qinghua Liu, Yu Bai +1
A unique challenge in Multi-Agent Reinforcement Learning (MARL) is the curse of multiagency, where the description length of the game as well as the complexity of many existing lea…
Learning Rationalizable Equilibria in Multiplayer Games
Yuanhao Wang, Dingwen Kong, Yu Bai +1
A natural goal in multiagent learning besides finding equilibria is to learn rationalizable behavior, where players learn to avoid iteratively dominated actions. However, even in t…
Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
Qinghua Liu, Yuanhao Wang, Chi Jin
An ideal strategy in zero-sum games should not only grant the player an average reward no less than the value of Nash equilibrium, but also exploit the (adaptive) opponents when th…
V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL
Chi Jin, Qinghua Liu, Yuanhao Wang +1
A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents, where the size of the joint action space scales exponentially with the number of agents.…
An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap
Yuanhao Wang, Ruosong Wang, Sham M. Kakade
A fundamental question in the theory of reinforcement learning is: suppose the optimal -function lies in the linear span of a given dimensional feature mapping, is sample-ef…
Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
Guodong Zhang, Yuanhao Wang, Laurent Lessard +1
Smooth minimax games often proceed by simultaneous or alternating gradient updates. Although algorithms with alternating updates are commonly used in practice, the majority of exis…
Refined Analysis of FPL for Adversarial Markov Decision Processes
Yuanhao Wang, Kefan Dong
We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unk…
On the Suboptimality of Negative Momentum for Minimax Optimization
Guodong Zhang, Yuanhao Wang
Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more comp…
Improved Algorithms for Convex-Concave Minimax Optimization
Yuanhao Wang, Jian Li
This paper studies minimax optimization problems , where is -strongly convex with respect to , -strongly concave with respect to and…
On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach
Yuanhao Wang, Guodong Zhang, Jimmy Ba
Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax…
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
Kefan Dong, Yuanhao Wang, Xiaoyu Chen +1
A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Recently, Jin et al. \cite{jin2018q} proposed a Q-learning algorithm with UC…
16-qubit IBM universal quantum computer can be fully entangled
Yuanhao Wang, Ying Li, Zhang-qi Yin +1
Entanglement is an important evidence that a quantum device can potentially solve problems intractable for classical computers. In this paper, we prepare connected graph states inv…