106 citations · 996 across the 72 of their papers we have counts for
73 papers
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Haipeng Luo, Qingfeng Sun, Can Xu +8
Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, mo…
Regret Matching+: (In)Stability and Fast Convergence in Games
Gabriele Farina, Julien Grand-Clément, Christian Kroer +2
Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery…
No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
Tiancheng Jin, Junyan Liu, Chloé Rouyer +3
Existing online learning algorithms for adversarial Markov Decision Processes achieve regret after rounds of interactions even if the loss functions are chosen…
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback
Yang Cai, Haipeng Luo, Chen-Yu Wei +1
We revisit the problem of learning in two-player zero-sum Markov games, focusing on developing an algorithm that is uncoupled, convergent, and rational, with non-asymptotic converg…
Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
Tiancheng Jin, Junyan Liu, Haipeng Luo
We study the problem of designing adaptive multi-armed bandit algorithms that perform optimally in both the stochastic setting and the adversarial setting simultaneously (often kno…
Practical Contextual Bandits with Feedback Graphs
Mengxiao Zhang, Yuheng Zhang, Olga Vrousgou +2
While contextual bandit has a mature theory, effectively leveraging different feedback patterns to enhance the pace of learning remains unclear. Bandits with feedback graphs, which…
ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
Akhil Agnihotri, Rahul Jain, Haipeng Luo
Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the disco…
Refined Regret for Adversarial MDPs with Linear Function Approximation
Yan Dai, Haipeng Luo, Chen-Yu Wei +1
We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over episodes and the state space can be arbitrarily large.…
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
Wenhao Wu, Haipeng Luo, Bo Fang +2
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences. However, in real-world scenarios, online…
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
Wenhao Wu, Xiaohan Wang, Haipeng Luo +3
Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such pow…
No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution
Mengxiao Zhang, Shi Chen, Haipeng Luo +1
Supply chain management (SCM) has been recognized as an important discipline with applications to many industries, where the two-echelon stochastic inventory model, involving one d…
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs
Haipeng Luo, Hanghang Tong, Mengxiao Zhang +1
We study high-probability regret bounds for adversarial -armed bandits with time-varying feedback graphs over rounds. For general strongly observable graphs, we develop an a…
Clairvoyant Regret Minimization: Equivalence with Nemirovski's Conceptual Prox Method and Extension to General Convex Games
Gabriele Farina, Christian Kroer, Chung-Wei Lee +1
A recent paper by Piliouras et al. [2021, 2022] introduces an uncoupled learning algorithm for normal-form games -- called Clairvoyant MWU (CMWU). In this note we show that CMWU is…
Near-Optimal No-Regret Learning Dynamics for General Convex Games
Gabriele Farina, Ioannis Anagnostides, Haipeng Luo +3
A recent line of work has established uncoupled learning dynamics such that, when employed by all players in a game, each player's \emph{regret} after repetitions grows polylog…
Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
Liyu Chen, Haipeng Luo
We initiate the study of dynamic regret minimization for goal-oriented reinforcement learning modeled by a non-stationary stochastic shortest path problem with changing cost and tr…
Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
Yan Dai, Haipeng Luo, Liyu Chen
We consider regret minimization for Adversarial Markov Decision Processes (AMDPs), where the loss functions are changing over time and adversarially chosen, and the learner only ob…
Uncoupled Learning Dynamics with Swap Regret in Multiplayer Games
Ioannis Anagnostides, Gabriele Farina, Christian Kroer +3
In this paper we establish efficient and \emph{uncoupled} learning dynamics so that, when employed by all players in a general-sum multiplayer game, the \emph{swap regret} of each…
Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits
Haipeng Luo, Mengxiao Zhang, Peng Zhao +1
We consider the problem of combining and learning over a set of adversarial bandit algorithms with the goal of adaptively tracking the best one on the fly. The CORRAL algorithm of…
Adaptive Bandit Convex Optimization with Heterogeneous Curvature
Haipeng Luo, Mengxiao Zhang, Peng Zhao
We consider the problem of adversarial bandit convex optimization, that is, online learning over a sequence of arbitrary convex loss functions with only one function evaluation for…
Policy Optimization for Stochastic Shortest Path
Liyu Chen, Haipeng Luo, Aviv Rosenberg
Policy optimization is among the most popular and successful reinforcement learning algorithms, and there is increasing interest in understanding its theoretical guarantees. In thi…
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
Gabriele Farina, Chung-Wei Lee, Haipeng Luo +1
While extensive-form games (EFGs) can be converted into normal-form games (NFGs), doing so comes at the cost of an exponential blowup of the strategy space. So, progress on NFGs an…
Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints
Liyu Chen, Rahul Jain, Haipeng Luo
We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with…
No-Regret Learning in Time-Varying Zero-Sum Games
Mengxiao Zhang, Peng Zhao, Haipeng Luo +1
Learning from repeated play in a fixed two-player zero-sum game is a classic problem in game theory and online learning. We consider a variant of this problem where the game payoff…
Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback
Tiancheng Jin, Tal Lancewicki, Haipeng Luo +2
The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observed in delay. This…