AI Agent - arXivDaily 专题

2305.16334 2023-05-29 cs.CL cs.AI 62%

OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

Yuanzhen Xie, Tao Xie, Mingxiong Lin, WenTao Wei, Chenglin Li, Beibei Kong, Lei Chen, Chengxiang Zhuo, Bo Hu, Zang Li

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

2304.10770 2023-05-19 cs.LG cs.AI cs.IT math.IT 62%

DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards

Shanchuan Wan, Yujin Tang, Yingtao Tian, Tomoyuki Kaneko

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

Comments Accepted as a conference paper to the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23)

2212.11636 2023-05-18 cs.LG cs.AI 62%

Towards Causal Credit Assignment

Mátyás Schubert

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

Comments In case I write a paper about this thesis, I do not want them to be duplicates of each other

2305.04432 2023-05-09 cs.LG cs.AI 62%

Goal-oriented inference of environment from redundant observations

Kazuki Takahashi, Tomoki Fukai, Yutaka Sakai, Takashi Takekawa

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

Comments 15 pages, 7 figures

2305.00654 2023-05-03 cs.LG cs.AI 62%

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Yash Chandak, Shantanu Thakoor, Zhaohan Daniel Guo, Yunhao Tang, Remi Munos, Will Dabney, Diana L Borsa

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

Comments Accepted at the 40th International Conference on Machine Learning (ICML 2023)

2304.14493 2023-05-01 cs.CV cs.AI cs.LG cs.RO 62%

Symmetry and Complexity in Object-Centric Deep Active Inference Models

Stefano Ferraro, Toon Van de Maele, Tim Verbelen, Bart Dhoedt

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

2304.12204 2023-04-25 cs.CV cs.AI cs.LG 62%

Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations

Dong Won Lee, Yubin Kim, Rosalind Picard, Cynthia Breazeal, Hae Won Park

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

Comments 7 pages, 4 figures, IJCAI

2304.10098 2023-04-25 cs.LG cs.AI 62%

Two-Memory Reinforcement Learning

Zhao Yang, Thomas. M. Moerland, Mike Preuss, Aske Plaat

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

2304.07219 2023-04-17 cs.LG cs.AI 62%

Model Predictive Control with Self-supervised Representation Learning

Jonas Matthies, Muhammad Burhan Hafez, Mostafa Kotb, Stefan Wermter

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

2304.00252 2023-04-11 cs.LG cs.AI cs.CR 62%

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

Hao Chen, Chen Gong, Yizhe Wang, Xinwen Hou

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

2304.00046 2023-04-04 cs.LG cs.AI 62%

Accelerating exploration and representation learning with offline pre-training

Bogdan Mazoure, Jake Bruce, Doina Precup, Rob Fergus, Ankit Anand

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

2303.01673 2023-03-10 cs.DS cs.AI cs.LG 62%

Near Optimal Memory-Regret Tradeoff for Online Learning

Binghui Peng, Aviad Rubinstein

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

2205.12258 2023-02-22 cs.LG cs.CL stat.ML 62%

History Compression via Language Models in Reinforcement Learning

Fabian Paischer, Thomas Adler, Vihang Patil, Angela Bitto-Nemling, Markus Holzleitner, Sebastian Lehner, Hamid Eghbal-zadeh, Sepp Hochreiter

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

Comments ICML 2022

2110.12810 2023-02-22 cs.LG cs.AI 62%

Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning

Alper Demir

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

Comments Acknowledgements are added. Appl Intell (2023)

2111.02574 2023-02-21 cs.CL cs.LG 62%

Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues

Mehrad Moradshahi, Victoria Tsai, Giovanni Campagna, Monica S. Lam

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

Comments Published in EACL 2023

2302.08734 2023-02-20 cs.AI cs.LG 62%

A State Augmentation based approach to Reinforcement Learning from Human Preferences

Mudit Verma, Subbarao Kambhampati

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

Comments R2HCAI, AAAI 2023

1706.03741 2023-02-20 stat.ML cs.AI cs.HC cs.LG 62%

Deep reinforcement learning from human preferences

Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei

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

2302.03851 2023-02-09 cs.LG cs.SE 62%

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines

Siyuan Chen, Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry

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

2209.13046 2023-01-31 cs.LG cs.AI 62%

Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective

Lunjun Zhang, Bradly C. Stadie

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

2206.11889 2023-01-10 cs.LG cs.AI cs.SY eess.SY math.OC stat.ML 62%

Provably Efficient Model-Free Constrained RL with Linear Function Approximation

Arnob Ghosh, Xingyu Zhou, Ness Shroff

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

Comments Accepted and Published at the 36th Neural Information Processing Systems (NeurIPS'22). Section J (where different episodes may start from different states) is added in this version

2210.05805 2023-01-06 cs.LG cs.AI 62%

Exploration via Elliptical Episodic Bonuses

Mikael Henaff, Roberta Raileanu, Minqi Jiang, Tim Rocktäschel

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

2004.04954 2023-01-06 cs.CV cs.AI cs.LG cs.RO 62%

Learning to Visually Navigate in Photorealistic Environments Without any Supervision

Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam, Armand Joulin, Piotr Bojanowski

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

2110.06206 2023-01-05 cs.LG cs.AI 62%

StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning

Jinghuan Shang, Kumara Kahatapitiya, Xiang Li, Michael S. Ryoo

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

Comments Accepted to ECCV 2022. Our code is available at https://github.com/elicassion/StARformer

2212.06988 2022-12-15 cs.LG cs.AI 62%

Efficient Exploration in Resource-Restricted Reinforcement Learning

Zhihai Wang, Taoxing Pan, Qi Zhou, Jie Wang

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

Comments Accepted to AAAI 2023

2212.02125 2022-12-06 stat.ML cs.AI cs.LG 62%

TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

Yuanying Cai, Chuheng Zhang, Li Zhao, Wei Shen, Xuyun Zhang, Lei Song, Jiang Bian, Tao Qin, Tieyan Liu

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

Comments Accepted by ICDM-22 (Best Student Paper Runner-Up Awards)

2212.00187 2022-12-02 cs.AI cs.LG 62%

Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

Nadia M. Ady, Roshan Shariff, Johannes Günther, Patrick M. Pilarski

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

Comments Submitted to the Journal of Artificial Intelligence Research (JAIR)

2211.16002 2022-11-30 cs.CL cs.AI 62%

DiffG-RL: Leveraging Difference between State and Common Sense

Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori

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

Comments Findings of EMNLP 2022. Code available at: https://github.com/ibm/diffg-rl

2208.08965 2022-11-29 cs.CV cs.AI cs.CL cs.MM 62%

GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement

Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mitamura, Alexander G. Hauptmann

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

Comments ACM Multimedia 2022 (Oral), Code: https://github.com/zhiqic/GSRFormer

2112.03235 2022-11-29 cs.AI cs.CE cs.LG cs.MS 62%

Simulation Intelligence: Towards a New Generation of Scientific Methods

Alexander Lavin, David Krakauer, Hector Zenil, Justin Gottschlich, Tim Mattson, Johann Brehmer, Anima Anandkumar, Sanjay Choudry, Kamil Rocki, Atılım Güneş Baydin, Carina Prunkl, Brooks Paige, Olexandr Isayev, Erik Peterson, Peter L. McMahon, Jakob Macke, Kyle Cranmer, Jiaxin Zhang, Haruko Wainwright, Adi Hanuka, Manuela Veloso, Samuel Assefa, Stephan Zheng, Avi Pfeffer

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

2211.10419 2022-11-21 q-bio.NC cs.AI cs.LG 62%

A Neural Active Inference Model of Perceptual-Motor Learning

Zhizhuo Yang, Gabriel J. Diaz, Brett R. Fajen, Reynold Bailey, Alexander Ororbia

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

Comments 16 pages including references, 6 figures. Submitted to Frontiers in Computational Neuroscience

1. 记忆与上下文管理 4786 篇

OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards

Towards Causal Credit Assignment

Goal-oriented inference of environment from redundant observations

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Symmetry and Complexity in Object-Centric Deep Active Inference Models

Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations

Two-Memory Reinforcement Learning

Model Predictive Control with Self-supervised Representation Learning

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

Accelerating exploration and representation learning with offline pre-training

Near Optimal Memory-Regret Tradeoff for Online Learning

History Compression via Language Models in Reinforcement Learning

Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning

Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues

A State Augmentation based approach to Reinforcement Learning from Human Preferences

Deep reinforcement learning from human preferences

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines

Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective

Provably Efficient Model-Free Constrained RL with Linear Function Approximation

Exploration via Elliptical Episodic Bonuses

Learning to Visually Navigate in Photorealistic Environments Without any Supervision

StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning

Efficient Exploration in Resource-Restricted Reinforcement Learning

TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

DiffG-RL: Leveraging Difference between State and Common Sense

GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement

Simulation Intelligence: Towards a New Generation of Scientific Methods

A Neural Active Inference Model of Perceptual-Motor Learning