23 citations · 87 across the 27 of their papers we have counts for
8 papers · 1 filter
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…