English
Related papers

Related papers: Geometric Value Iteration: Dynamic Error-Aware KL …

200 papers

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their…

Machine Learning · Computer Science 2024-04-16 Huozhi Zhou , Jinglin Chen , Lav R. Varshney , Ashish Jagmohan

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

Artificial Intelligence · Computer Science 2025-11-07 Zeng Zhiyuan , Jiashuo Liu , Zhangyue Yin , Ge Zhang , Wenhao Huang , Xipeng Qiu

Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, leading…

Computation and Language · Computer Science 2026-04-21 Renren Jin , Pengzhi Gao , Yuqi Ren , Zhuowen Han , Tongxuan Zhang , Wuwei Huang , Wei Liu , Jian Luan , Deyi Xiong

Regularization is critical for solving ill-posed geophysical inverse problems. Explicit regularization is often used, but there are opportunities to explore the implicit regularization effects that are inherent in a Neural Network…

Machine Learning · Computer Science 2024-07-10 Anran Xu , Lindsey J. Heagy

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevalent group-based algorithms such as GRPO require multi-rollout…

Machine Learning · Computer Science 2025-12-23 Rui Liu , Dian Yu , Lei Ke , Haolin Liu , Yujun Zhou , Zhenwen Liang , Haitao Mi , Pratap Tokekar , Dong Yu

An ongoing challenge in neural information processing is: how do neurons adjust their connectivity to improve task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning…

Neural and Evolutionary Computing · Computer Science 2021-06-01 Aman Bhargava , Mohammad R. Rezaei , Milad Lankarany

Reinforcement learning with verifiable rewards (RLVR) scales the reasoning ability of large language models (LLMs) but remains bottlenecked by limited labeled samples for continued data scaling. Reinforcement learning with intrinsic rewards…

Machine Learning · Computer Science 2025-10-13 Chuyi Tan , Peiwen Yuan , Xinglin Wang , Yiwei Li , Shaoxiong Feng , Yueqi Zhang , Jiayi Shi , Ji Zhang , Boyuan Pan , Yao Hu , Kan Li

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present…

Machine Learning · Computer Science 2025-10-13 Jing Li , Zhijie Sun , Zhicheng Zhou , Suming Qiu , Junjie Huang , Haijia Sun , Linyuan Qiu

This paper proposes a versatile covariate adjustment method that directly incorporates covariate balance in regression discontinuity (RD) designs. The new empirical entropy balancing method reweights the standard local polynomial RD…

Econometrics · Economics 2024-05-29 Jun Ma , Zhengfei Yu

Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…

Machine Learning · Computer Science 2026-01-27 Mingyuan Fan , Weiguang Han , Daixin Wang , Cen Chen , Zhiqiang Zhang , Jun Zhou

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value…

Machine Learning · Computer Science 2025-07-08 Ju-Seung Byun , Andrew Perrault

Deep reinforcement learning (RL) is a data-driven, model-free method capable of discovering complex control strategies for macroscopic objectives in high-dimensional systems, making its application towards flow control promising. Many…

Machine Learning · Computer Science 2021-07-21 Kevin Zeng , Michael D. Graham

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

This research proposes an enhancement to the innovative portfolio optimization approach using the G-Learning algorithm, combined with parametric optimization via the GIRL algorithm (G-learning approach to the setting of Inverse…

Portfolio Management · Quantitative Finance 2025-11-25 Fermat Leukam , Rock Stephane Koffi , Prudence Djagba

Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation…

Machine Learning · Computer Science 2026-02-20 Yan Sun , Jia Guo , Stanley Kok , Zihao Wang , Zujie Wen , Zhiqiang Zhang

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

Machine Learning · Computer Science 2024-02-26 Zhishuai Liu , Pan Xu

Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate…

Artificial Intelligence · Computer Science 2026-02-02 Hao Yi , Yulan Hu , Xin Li , Sheng Ouyang , Lizhong Ding , Yong Liu

In modern biomedical and econometric studies, longitudinal processes are often characterized by complex time-varying associations and abrupt regime shifts that are shared across correlated outcomes. Standard functional data analysis (FDA)…

Methodology · Statistics 2026-01-28 Baolin Chen , Mengfei Ran

This paper investigates the efficiency of the K-fold cross-validation (CV) procedure and a debiased version thereof as a means of estimating the generalization risk of a learning algorithm. We work under the general assumption of uniform…

Statistics Theory · Mathematics 2023-06-13 Anass Aghbalou , François Portier , Anne Sabourin