Tong Yang

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF