Yang, Tong
28 publications
NeurIPS
2025
Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
ICML
2025
Incentivize Without Bonus: Provably Efficient Model-Based Online Multi-Agent RL for Markov Games
NeurIPS
2025
Multi-Head Transformers Provably Learn Symbolic Multi-Step Reasoning via Gradient Descent
NeurIPS
2024
Federated Natural Policy Gradient and Actor Critic Methods for Multi-Task Reinforcement Learning
NeurIPS
2024
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
ICMLW
2024
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
NeurIPS
2023
Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
ICLR
2023
Solving Constrained Variational Inequalities via a First-Order Interior Point-Based Method