中文
相关论文

相关论文: Smaller Abstract State Spaces Enable Cross-Scale G…

200 篇论文

This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment. We assume that the…

机器学习 · 计算机科学 2024-07-09 Ainur Zhaikhan , Ali H. Sayed

Recent progress has pushed AI frontiers from pattern recognition tasks toward problems that require step by step, System2 style reasoning, especially with large language models. Yet, unlike learning, where generalization and out of…

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores…

人工智能 · 计算机科学 2025-11-11 Mingde "Harry" Zhao

Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state abstraction…

机器学习 · 计算机科学 2023-11-16 Rolf A. N. Starre , Marco Loog , Elena Congeduti , Frans A. Oliehoek

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

机器学习 · 计算机科学 2009-12-30 Marcus Hutter

Due to information asymmetry, finding optimal policies for Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) is hard with the complexity growing doubly exponentially in the horizon length. The challenge increases…

机器学习 · 计算机科学 2021-10-26 Hsu Kao , Vijay Subramanian

Deep models often fail to generalize well in test domains when the data distribution differs from that in the training domain. Among numerous approaches to address this Out-of-Distribution (OOD) generalization problem, there has been a…

机器学习 · 计算机科学 2022-10-14 Qixun Wang , Yifei Wang , Hong Zhu , Yisen Wang

Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been…

机器学习 · 计算机科学 2026-05-22 Clarisse Wibault , Alexander Goldie , Antonio Villares , Maike Osborne , Jakob Foerster

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Li Gu , Zihuan Jiang , Zhixiang Chi , Huan Liu , Ziqiang Wang , Yuanhao Yu , Glen Berseth , Yang Wang

Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings.…

机器学习 · 计算机科学 2021-02-15 Amy Zhang , Shagun Sodhani , Khimya Khetarpal , Joelle Pineau

Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In this work, we investigate the challenge of agentic post-training when the eventual test domains are unknown.…

人工智能 · 计算机科学 2026-01-27 Zhihan Liu , Lin Guan , Yixin Nie , Kai Zhang , Zhuoqun Hao , Lin Chen , Asli Celikyilmaz , Zhaoran Wang , Na Zhang

Real-world decision-making problems are often partially observable, and many can be formulated as a Partially Observable Markov Decision Process (POMDP). When we apply reinforcement learning (RL) algorithms to the POMDP, reasonable…

人工智能 · 计算机科学 2023-04-20 Soichiro Nishimori , Sotetsu Koyamada , Shin Ishii

A challenge in multi-agent reinforcement learning is to be able to generalize over intractable state-action spaces. Inspired from Tesseract [Mahajan et al., 2021], this position paper investigates generalisation in state-action space over…

机器学习 · 计算机科学 2021-10-28 Pascal Van Der Vaart , Anuj Mahajan , Shimon Whiteson

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

机器学习 · 计算机科学 2026-01-26 Chengyang Ying , Xinning Zhou , Zhongkai Hao , Hang Su , Songming Liu , Dong Yan , Jun Zhu

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and…

机器学习 · 计算机科学 2026-01-29 Burak Demirel , Yu Wang , Cristian Tatino , Pablo Soldati

Evaluating policies using off-policy data is crucial for applying reinforcement learning to real-world problems such as healthcare and autonomous driving. Previous methods for off-policy evaluation (OPE) generally suffer from high variance…

机器学习 · 计算机科学 2024-10-04 Shreyas Chaudhari , Ameet Deshpande , Bruno Castro da Silva , Philip S. Thomas

We design a simple reinforcement learning (RL) agent that implements an optimistic version of $Q$-learning and establish through regret analysis that this agent can operate with some level of competence in any environment. While we leverage…

机器学习 · 计算机科学 2021-07-13 Shi Dong , Benjamin Van Roy , Zhengyuan Zhou

Generalization is a central challenge for the deployment of reinforcement learning (RL) systems in the real world. In this paper, we show that the sequential structure of the RL problem necessitates new approaches to generalization beyond…

机器学习 · 计算机科学 2021-07-14 Dibya Ghosh , Jad Rahme , Aviral Kumar , Amy Zhang , Ryan P. Adams , Sergey Levine

Planning plays an important role in the broad class of decision theory. Planning has drawn much attention in recent work in the robotics and sequential decision making areas. Recently, Reinforcement Learning (RL), as an agent-environment…

人工智能 · 计算机科学 2016-08-18 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust…

机器学习 · 计算机科学 2020-08-04 Xingyu Lu , Kimin Lee , Pieter Abbeel , Stas Tiomkin