AI Agent - arXivDaily 专题

1810.01992 2018-10-05 cs.AI cs.LG 62%

Action Model Acquisition using LSTM

Ankuj Arora, Humbert Fiorino, Damien Pellier, Sylvie Pesty

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

Comments 13 pages

1810.00361 2018-10-02 cs.LG cs.AI stat.ML 62%

Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning

Gino Brunner, Manuel Fritsche, Oliver Richter, Roger Wattenhofer

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1809.01816 2018-09-07 cs.CV cs.AI cs.CL 62%

Visual Coreference Resolution in Visual Dialog using Neural Module Networks

Satwik Kottur, José M. F. Moura, Devi Parikh, Dhruv Batra, Marcus Rohrbach

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

Comments ECCV 2018 + results on VisDial v1.0 dataset

1803.05402 2018-09-07 cs.AI cs.LG stat.ML 62%

Imitation Learning with Concurrent Actions in 3D Games

Jack Harmer, Linus Gisslén, Jorge del Val, Henrik Holst, Joakim Bergdahl, Tom Olsson, Kristoffer Sjöö, Magnus Nordin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1807.01960 2018-07-06 cs.LG cs.AI stat.ML 62%

Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks

Georgios Papoudakis, Kyriakos C. Chatzidimitriou, Pericles A. Mitkas

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 4 pages, 3 figures, 3 tables

1801.01968 2018-06-05 cs.LG cs.AI 62%

Faster Deep Q-learning using Neural Episodic Control

Daichi Nishio, Satoshi Yamane

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 6 pages, 6 figures, COMPSAC2018 short paper

1803.05262 2018-05-29 cs.LG cs.AI 62%

Learning to Play General Video-Games via an Object Embedding Network

William Woof, Ke Chen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in IEEE CIG2018

1805.08966 2018-05-24 cs.LG cs.AI stat.ML 62%

Discovering Blind Spots in Reinforcement Learning

Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey, Julie Shah, Eric Horvitz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear at AAMAS 2018

1805.07603 2018-05-22 cs.LG cs.AI stat.ML 62%

Episodic Memory Deep Q-Networks

Zichuan Lin, Tianqi Zhao, Guangwen Yang, Lintao Zhang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted by IJCAI 2018

1707.00524 2018-04-30 cs.LG cs.AI stat.ML 62%

Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning

Haiyan Yin, Jianda Chen, Sinno Jialin Pan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1802.06428 2018-02-20 cs.LG cs.CL stat.ML 62%

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation

Fengyi Tang, Kaixiang Lin, Ikechukwu Uchendu, Hiroko H. Dodge, Jiayu Zhou

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL、cs.LG

Comments 9 pages, 4 figures, 4 tables

1601.07358 2018-02-14 quant-ph cs.AI cs.LG 62%

Quantum machine learning with glow for episodic tasks and decision games

Jens Clausen, Hans J. Briegel

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 14 figures

Journal ref Phys. Rev. A 97, 022303 (2018)

1710.10044 2017-10-30 cs.AI cs.LG stat.ML 62%

Distributional Reinforcement Learning with Quantile Regression

Will Dabney, Mark Rowland, Marc G. Bellemare, Rémi Munos

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1710.06574 2017-10-19 cs.AI cs.LG stat.ML 62%

The Effects of Memory Replay in Reinforcement Learning

Ruishan Liu, James Zou

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1706.06617 2017-06-22 cs.LG cs.AI stat.ML 62%

Observational Learning by Reinforcement Learning

Diana Borsa, Bilal Piot, Rémi Munos, Olivier Pietquin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1705.08997 2017-05-26 cs.AI cs.LG stat.ML 62%

State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

Himanshu Sahni, Saurabh Kumar, Farhan Tejani, Yannick Schroecker, Charles Isbell

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 5 pages, 6 figures; 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2017), Ann Arbor, Michigan

1605.09674 2017-01-30 cs.LG cs.AI cs.RO stat.ML 62%

VIME: Variational Information Maximizing Exploration

Rein Houthooft, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in Advances in Neural Information Processing Systems 29 (NIPS), pages 1109-1117

1701.04113 2017-01-17 cs.LG cs.AI 62%

Near Optimal Behavior via Approximate State Abstraction

David Abel, D. Ellis Hershkowitz, Michael L. Littman

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

Comments Earlier version published at ICML 2016

1612.00475 2016-12-05 stat.ML cs.AI cs.LG 62%

Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes

Taylor Killian, George Konidaris, Finale Doshi-Velez

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Brief abstract for poster submission to Machine Learning for Healthcare workshop at NIPS 2016

1605.07700 2016-05-26 cs.LG cs.AI 62%

Learning Purposeful Behaviour in the Absence of Rewards

Marlos C. Machado, Michael Bowling

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Extended version of the paper presented at the workshop entitled Abstraction in Reinforcement Learning, at the 33rd International Conference on Machine Learning, New York, NY, USA, 2016

1510.08906 2016-05-12 stat.ML cs.AI cs.LG 62%

Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning

Christoph Dann, Emma Brunskill

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 28 pages, appeared in Neural Information Processing Systems (NIPS) 2015, updated version with fixed typos and modified Lemma 1 and Lemma C.5

1605.01335 2016-05-05 cs.LG cs.AI 62%

Learning from the memory of Atari 2600

Jakub Sygnowski, Henryk Michalewski

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1508.04186 2015-10-16 cs.LG cs.AI cs.DC cs.NE 62%

Distributed Deep Q-Learning

Hao Yi Ong, Kevin Chavez, Augustus Hong

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Updated figure of distributed deep learning architecture, updated content throughout paper including dealing with minor grammatical issues and highlighting differences of our paper with respect to prior work. arXiv admin note: text overlap with arXiv:1312.5602 by other authors

1506.03379 2015-09-23 cs.LG cs.AI 62%

The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning

Emma Brunskill, Lihong Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages

1102.1027 2015-03-18 cs.IR cs.AI cs.LG nlin.AO q-bio.OT 62%

Collective Classification of Textual Documents by Guided Self-Organization in T-Cell Cross-Regulation Dynamics

Alaa Abi-Haidar, Luis M. Rocha

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Evolutionary Intelligence. 2011. Volume 4, Number 2, 69-80

1407.3341 2014-07-15 cs.AI cs.LG 62%

Extreme State Aggregation Beyond MDPs

Marcus Hutter

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 28 LaTeX pages. 8 Theorems

1402.0560 2014-02-05 cs.LG cs.AI 62%

Safe Exploration of State and Action Spaces in Reinforcement Learning

Javier Garcia, Fernando Fernandez

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Journal Of Artificial Intelligence Research, Volume 45, pages 515-564, 2012

1106.0681 2011-06-06 cs.LG cs.AI 62%

Accelerating Reinforcement Learning through Implicit Imitation

C. Boutilier, B. Price

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Journal Of Artificial Intelligence Research, Volume 19, pages 569-629, 2003

cs/0404032 2009-12-01 cs.LG cs.AI cs.NE 62%

When Do Differences Matter? On-Line Feature Extraction Through Cognitive Economy

David J. Finton

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 10 PostScript figures, LaTeX2e

2608.03420 2026-08-05 cs.AI 新提交 61%

Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory

基于经验记忆提升大语言模型智能体的序列决策能力

Jakub Rada, Viliam Lisý

专题命中记忆与上下文管理：agentic(abstract)；分类 cs.AI；autonomous agent(comments)

AI总结本研究针对LLM智能体序列决策性能不足的问题，提出带经验记忆的智能体框架，通过对局后反思与规则提取，在不修改模型权重的情况下提升了井字棋任务的表现。

Comments 8 pages, 6 figures, 14 tables, 5 appendices, accepted at Neuro-Symbolic Intelligence for LLMs and Autonomous Agents workshop at IJCAI 2026

1. 记忆与上下文管理 4753 篇

Action Model Acquisition using LSTM

Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning

Visual Coreference Resolution in Visual Dialog using Neural Module Networks

Imitation Learning with Concurrent Actions in 3D Games

Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks

Faster Deep Q-learning using Neural Episodic Control

Learning to Play General Video-Games via an Object Embedding Network

Discovering Blind Spots in Reinforcement Learning

Episodic Memory Deep Q-Networks

Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation

Quantum machine learning with glow for episodic tasks and decision games

Distributional Reinforcement Learning with Quantile Regression

The Effects of Memory Replay in Reinforcement Learning

Observational Learning by Reinforcement Learning

State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

VIME: Variational Information Maximizing Exploration

Near Optimal Behavior via Approximate State Abstraction

Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes

Learning Purposeful Behaviour in the Absence of Rewards

Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning

Learning from the memory of Atari 2600

Distributed Deep Q-Learning

The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning

Collective Classification of Textual Documents by Guided Self-Organization in T-Cell Cross-Regulation Dynamics

Extreme State Aggregation Beyond MDPs

Safe Exploration of State and Action Spaces in Reinforcement Learning

Accelerating Reinforcement Learning through Implicit Imitation

When Do Differences Matter? On-Line Feature Extraction Through Cognitive Economy

Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory