23 citations · 87 across the 27 of their papers we have counts for
27 papers
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…
No-Regret Linear Bandits under Gap-Adjusted Misspecification
Chong Liu, Dan Qiao, Ming Yin +2
This work studies linear bandits under a new notion of gap-adjusted misspecification and is an extension of Liu et al. (2023). When the underlying reward function is not linear, ex…
On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures
Ming Yin, Mengdi Wang, Yu-Xiang Wang
This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline…
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Momin Haider, Ming Yin, Menglei Zhang +3
Mobile devices such as smartphones, laptops, and tablets can often connect to multiple access networks (e.g., Wi-Fi, LTE, and 5G) simultaneously. Recent advancements facilitate sea…
Learning the Target Network in Function Space
Kavosh Asadi, Yao Liu, Shoham Sabach +2
We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ens…
Transfer Q Star: Principled Decoding for LLM Alignment
Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin +4
Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billi…
Offline Multitask Representation Learning for Reinforcement Learning
Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng +4
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common repr…
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang, Ming Yin, Mengdi Wang +2
Recent studies in reinforcement learning (RL) have made significant progress by leveraging function approximation to alleviate the sample complexity hurdle for better performance.…
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Xiang Yue, Yuansheng Ni, Kai Zhang +19
We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU…
Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
Songtao Feng, Ming Yin, Yu-Xiang Wang +2
The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for fi…
Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data
Sunil Madhow, Dan Qiao, Ming Yin +1
Developing theoretical guarantees on the sample complexity of offline RL methods is an important step towards making data-hungry RL algorithms practically viable. Currently, most r…
Non-stationary Reinforcement Learning under General Function Approximation
Songtao Feng, Ming Yin, Ruiquan Huang +3
General function approximation is a powerful tool to handle large state and action spaces in a broad range of reinforcement learning (RL) scenarios. However, theoretical understand…
TheoremQA: A Theorem-driven Question Answering dataset
Wenhu Chen, Ming Yin, Max Ku +6
The recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy. However, their capabilities to s…
Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs
Dan Qiao, Ming Yin, Yu-Xiang Wang
In many real-life reinforcement learning (RL) problems, deploying new policies is costly. In those scenarios, algorithms must solve exploration (which requires adaptivity) while sw…
No-Regret Linear Bandits beyond Realizability
Chong Liu, Ming Yin, Yu-Xiang Wang
We study linear bandits when the underlying reward function is not linear. Existing work relies on a uniform misspecification parameter that measures the sup-norm error of the…
Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
Ming Yin, Mengdi Wang, Yu-Xiang Wang
Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-O…
Offline Reinforcement Learning with Closed-Form Policy Improvement Operators
Jiachen Li, Edwin Zhang, Ming Yin +3
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a poli…
On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Thanh Nguyen-Tang, Ming Yin, Sunil Gupta +2
Sample-efficient offline reinforcement learning (RL) with linear function approximation has recently been studied extensively. Much of prior work has yielded the minimax-optimal bo…
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
Kaiqi Zhang, Ming Yin, Yu-Xiang Wang
Quantized neural networks have drawn a lot of attention as they reduce the space and computational complexity during the inference. Moreover, there has been folklore that quantizat…
Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
Ming Yin, Wenjing Chen, Mengdi Wang +1
Goal-oriented Reinforcement Learning, where the agent needs to reach the goal state while simultaneously minimizing the cost, has received significant attention in real-world appli…
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
Ming Yin, Yaqi Duan, Mengdi Wang +1
Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. D…
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Dan Qiao, Ming Yin, Ming Min +1
We study the problem of reinforcement learning (RL) with low (policy) switching cost - a problem well-motivated by real-life RL applications in which deployments of new policies ar…
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism
Ming Yin, Yu-Xiang Wang
We study the offline reinforcement learning (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown Markov Decision Process (MDP) using the data c…
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings
Ming Yin, Yu-Xiang Wang
This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified fram…