English
Related papers

Related papers: Delay-Adapted Policy Optimization and Improved Reg…

200 papers

Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations about \texttt{DPO}. First, we show that \texttt{DPO} loss…

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Machine Learning · Computer Science 2026-05-21 Zhanhong Jiang

We present a modified tuning of the algorithm of Zimmert and Seldin [2020] for adversarial multiarmed bandits with delayed feedback, which in addition to the minimax optimal adversarial regret guarantee shown by Zimmert and Seldin…

Machine Learning · Computer Science 2022-07-01 Saeed Masoudian , Julian Zimmert , Yevgeny Seldin

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

Machine Learning · Computer Science 2024-10-29 Jianmina Ma , Jingtian Ji , Yue Gao

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

We propose a new best-of-both-worlds algorithm for bandits with variably delayed feedback. In contrast to prior work, which required prior knowledge of the maximal delay $d_{\mathrm{max}}$ and had a linear dependence of the regret on it,…

Machine Learning · Computer Science 2024-05-29 Saeed Masoudian , Julian Zimmert , Yevgeny Seldin

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

Learning at the edges has become increasingly important as large quantities of data are continually generated locally. Among others, this paradigm requires algorithms that are simple (so that they can be executed by local devices), robust…

Machine Learning · Computer Science 2024-02-06 Tuan-Anh Nguyen , Nguyen Kim Thang , Denis Trystram

Online learning with delayed feedback has received increasing attention recently due to its several applications in distributed, web-based learning problems. In this paper we provide a systematic study of the topic, and analyze the effect…

Machine Learning · Computer Science 2015-07-02 Pooria Joulani , András György , Csaba Szepesvári

We investigate an infinite-horizon average reward Markov Decision Process (MDP) with delayed, composite, and partially anonymous reward feedback. The delay and compositeness of rewards mean that rewards generated as a result of taking an…

Machine Learning · Computer Science 2023-08-29 Washim Uddin Mondal , Vaneet Aggarwal

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Artificial Intelligence · Computer Science 2024-12-25 Jiacai Liu , Chaojie Wang , Chris Yuhao Liu , Liang Zeng , Rui Yan , Yiwen Sun , Yang Liu , Yahui Zhou

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Machine Learning · Computer Science 2019-10-01 Zhenyu Zhang , Xiangfeng Luo , Tong Liu , Shaorong Xie , Jianshu Wang , Wei Wang , Yang Li , Yan Peng

Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is…

Machine Learning · Computer Science 2019-12-13 Lior Shani , Yonathan Efroni , Shie Mannor

Although online convex optimization (OCO) under arbitrary delays has received increasing attention recently, previous studies focus on stationary environments with the goal of minimizing static regret. In this paper, we investigate the…

Machine Learning · Computer Science 2025-11-10 Yuanyu Wan , Chang Yao , Yitao Ma , Mingli Song , Lijun Zhang

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

Machine Learning · Computer Science 2026-03-03 Yijing Ke , Zihan Zhang , Ruosong Wang

We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinite-horizon discounted Markov decision process (MDP). While existing analyses of common approaches, such as fitted $Q$-iteration…

Machine Learning · Computer Science 2023-07-13 Yichun Hu , Nathan Kallus , Masatoshi Uehara

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While…

Machine Learning · Computer Science 2026-05-04 Haichen Hu , Jian Qian , David Simchi-Levi

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

Computation and Language · Computer Science 2025-07-29 Songjun Tu , Jiahao Lin , Xiangyu Tian , Qichao Zhang , Linjing Li , Yuqian Fu , Nan Xu , Wei He , Xiangyuan Lan , Dongmei Jiang , Dongbin Zhao

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…

Machine Learning · Computer Science 2024-05-31 Weiye Zhao , Feihan Li , Yifan Sun , Rui Chen , Tianhao Wei , Changliu Liu

Proximal policy optimization(PPO) has been proposed as a first-order optimization method for reinforcement learning. We should notice that an exterior penalty method is used in it. Often, the minimizers of the exterior penalty functions…

Machine Learning · Computer Science 2018-12-18 Cheng Zeng , Hongming Zhang