中文
相关论文

相关论文: Which Experiences Are Influential for RL Agents? E…

200 篇论文

Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper, we conduct an empirical study on how memory management…

人工智能 · 计算机科学 2025-10-14 Zidi Xiong , Yuping Lin , Wenya Xie , Pengfei He , Zirui Liu , Jiliang Tang , Himabindu Lakkaraju , Zhen Xiang

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

机器学习 · 计算机科学 2021-12-09 Liran Szlak , Ohad Shamir

One of the key challenges of Reinforcement Learning (RL) is the ability of agents to generalise their learned policy to unseen settings. Moreover, training RL agents requires large numbers of interactions with the environment. Motivated by…

机器学习 · 计算机科学 2024-12-10 Alain Andres , Lukas Schäfer , Stefano V. Albrecht , Javier Del Ser

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

机器人学 · 计算机科学 2022-05-31 Haochen Liu , Zhiyu Huang , Jingda Wu , Chen Lv

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

机器学习 · 计算机科学 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things…

人工智能 · 计算机科学 2022-07-21 Samuel Allen Alexander , Michael Castaneda , Kevin Compher , Oscar Martinez

Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to…

机器学习 · 计算机科学 2021-01-05 Qiang He , Xinwen Hou

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This…

机器学习 · 计算机科学 2024-01-30 Burcu Küçükoğlu , Walraaf Borkent , Bodo Rueckauer , Nasir Ahmad , Umut Güçlü , Marcel van Gerven

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve…

人工智能 · 计算机科学 2026-02-24 Yi Wan , Jiuqi Wang , Liam Li , Jinsong Liu , Ruihao Zhu , Zheqing Zhu

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…

机器学习 · 计算机科学 2026-03-16 Yueheng Li , Guangming Xie , Zongqing Lu

Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Behavior estimation aims…

机器学习 · 计算机科学 2023-05-29 Guoxi Zhang , Hisashi Kashima

Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a…

人工智能 · 计算机科学 2022-04-07 Joseph Christian G. Noel

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward…

人工智能 · 计算机科学 2026-03-03 Fanqi Kong , Jiayi Zhang , Mingyi Deng , Chenglin Wu , Yuyu Luo , Bang Liu

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience. These outcome-conditioned imitation learning methods are…

机器学习 · 计算机科学 2023-02-21 Benjamin Eysenbach , Soumith Udatha , Sergey Levine , Ruslan Salakhutdinov

We present an approach for the quantification of the usefulness of transfer in reinforcement learning via regret bounds for a multi-agent setting. Considering a number of $\aleph$ agents operating in the same Markov decision process,…

机器学习 · 计算机科学 2025-11-14 Adrienne Tuynman , Ronald Ortner

In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which…

机器学习 · 统计学 2013-07-19 Mohammad Gheshlaghi Azar , Alessandro Lazaric , Emma Brunskill

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require…

计算与语言 · 计算机科学 2026-03-25 Guoqing Wang , Sunhao Dai , Guangze Ye , Zeyu Gan , Wei Yao , Yong Deng , Xiaofeng Wu , Zhenzhe Ying

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

机器学习 · 计算机科学 2022-11-30 Jingda Wu , Zhiyu Huang , Wenhui Huang , Chen Lv

For many space applications, traditional control methods are often used during operation. However, as the number of space assets continues to grow, autonomous operation can enable rapid development of control methods for different space…

机器学习 · 计算机科学 2024-05-22 Nathaniel Hamilton , Kyle Dunlap , Kerianne L. Hobbs