中文
相关论文

相关论文: The Challenges of Exploration for Offline Reinforc…

200 篇论文

Imitation learning has proven effective for training robots to perform complex tasks from expert human demonstrations. However, it remains limited by its reliance on high-quality, task-specific data, restricting adaptability to the diverse…

Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over…

机器学习 · 计算机科学 2025-09-01 Yunpeng Qing , Shunyu Liu , Jie Song , Yang Zhou , Kaixuan Chen , Huiqiong Wang , Mingli Song

The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing…

计算机视觉与模式识别 · 计算机科学 2024-03-28 Valay Bundele , Mahesh Bhupati , Biplab Banerjee , Aditya Grover

Existing theoretical studies on offline reinforcement learning (RL) mostly consider a dataset sampled directly from the target task. In practice, however, data often come from several heterogeneous but related sources. Motivated by this…

机器学习 · 统计学 2023-06-16 Chengshuai Shi , Wei Xiong , Cong Shen , Jing Yang

Offline-to-Online Reinforcement Learning has emerged as a powerful paradigm, leveraging offline data for initialization and online fine-tuning to enhance both sample efficiency and performance. However, most existing research has focused on…

人工智能 · 计算机科学 2026-03-05 Hai Zhong , Xun Wang , Zhuoran Li , Longbo Huang

In this work we revisit the Mobility Robustness Optimisation (MRO) algorithm and study the possibility of learning the optimal Cell Individual Offset tuning using offline Reinforcement Learning. Such methods make use of collected offline…

网络与互联网体系结构 · 计算机科学 2025-07-01 Pegah Alizadeh , Anastasios Giovanidis , Pradeepa Ramachandra , Vasileios Koutsoukis , Osama Arouk

In this study, we aim to enhance the arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization and elucidate…

计算与语言 · 计算机科学 2024-03-08 Hao Sun , Alihan Hüyük , Mihaela van der Schaar

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in…

机器学习 · 计算机科学 2024-02-21 Avinandan Bose , Simon Shaolei Du , Maryam Fazel

Model-based reinforcement learning (MBRL) algorithms learn a dynamics model from collected data and apply it to generate synthetic trajectories to enable faster learning. This is an especially promising paradigm in offline reinforcement…

机器学习 · 计算机科学 2024-08-21 Padmanaba Srinivasan , William Knottenbelt

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not…

机器学习 · 计算机科学 2025-11-11 Guojian Wang , Jianxiang Liu , Xinyuan Li , Faguo Wu , Xiao Zhang , Tianyuan Chen , Xuyang Chen

Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…

人工智能 · 计算机科学 2025-10-22 Jongchan Park , Mingyu Park , Donghwan Lee

Off-dynamics reinforcement learning (RL), where training and deployment transition dynamics are different, can be formulated as learning in a robust Markov decision process (RMDP) where uncertainties in transition dynamics are imposed.…

机器学习 · 计算机科学 2025-11-10 Yiting He , Zhishuai Liu , Weixin Wang , Pan Xu

Not having access to compact and meaningful representations is known to significantly increase the complexity of reinforcement learning (RL). For this reason, it can be useful to perform state representation learning (SRL) before tackling…

机器学习 · 计算机科学 2022-02-16 Astrid Merckling , Nicolas Perrin-Gilbert , Alex Coninx , Stéphane Doncieux

In many reinforcement learning (RL) applications one cannot easily let the agent act in the world; this is true for autonomous vehicles, healthcare applications, and even some recommender systems, to name a few examples. Offline RL provides…

机器学习 · 计算机科学 2024-07-02 Ori Linial , Guy Tennenholtz , Uri Shalit

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

机器学习 · 计算机科学 2023-03-14 Ziniu Li , Ke Xu , Liu Liu , Lanqing Li , Deheng Ye , Peilin Zhao

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

机器学习 · 计算机科学 2020-10-06 Giorgio Angelotti , Nicolas Drougard , Caroline Ponzoni Carvalho Chanel

In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment. However in many real-world applications, access to the environment is limited to a fixed offline dataset of logged…

机器学习 · 计算机科学 2019-11-27 Yifan Wu , George Tucker , Ofir Nachum

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…

人工智能 · 计算机科学 2025-01-28 Alberto Castagna

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

机器学习 · 计算机科学 2023-05-25 Chenjie Mao

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively…

‹ 上一页 1 8 9 10 下一页 ›