1 citations · 2 across the 9 of their papers we have counts for
7 papers · 1 filter
Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
Anupam Nayak, Tong Yang, Osman Yagan +2
Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired trait…
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
Tong Yang, Yu Huang, Yingbin Liang +1
Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities thr…
Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
Tong Yang, Bo Dai, Lin Xiao +1
Multi-agent reinforcement learning (MARL) lies at the heart of a plethora of applications involving the interaction of a group of agents in a shared unknown environment. A prominen…
Faster WIND: Accelerating Iterative Best-of- Distillation for LLM Alignment
Tong Yang, Jincheng Mei, Hanjun Dai +5
Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-N distillation (BOND). However, the iterative BOND algo…
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Tong Yang, Yu Huang, Yingbin Liang +1
In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoreti…
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
Shicong Cen, Jincheng Mei, Katayoon Goshvadi +6
Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of pr…
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
Tong Yang, Shicong Cen, Yuting Wei +2
Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a mult…