AI Agent - arXivDaily 专题

2405.05066 2024-05-09 cs.AI cs.CY cs.LG 62%

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Karim Hamade, Reid McIlroy-Young, Siddhartha Sen, Jon Kleinberg, Ashton Anderson

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

Comments 18 pages, 5 figures, 15 tables, Published In The Twelfth International Conference on Learning Representations, ICLR 2024

2009.09538 2024-05-07 cs.LG cs.AI stat.ML 62%

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms

Mengfan Xu, Diego Klabjan

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

Comments 40 pages, 8 figures

2405.01684 2024-05-06 cs.LG cs.AI 62%

Intelligent Switching for Reset-Free RL

Darshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar

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

Comments Published at ICLR 2024

1511.04143 2024-05-06 cs.AI cs.LG cs.MA cs.NE 62%

Deep Reinforcement Learning in Parameterized Action Space

Matthew Hausknecht, Peter Stone

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

2405.00723 2024-05-03 eess.SP cs.AI cs.LG 62%

EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networks

Htoo Wai Aung, Jiao Jiao Li, Yang An, Steven W. Su

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

2402.18002 2024-05-01 cs.RO cs.AI cs.LG 62%

Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist

Hai Nguyen, Tadashi Kozuno, Cristian C. Beltran-Hernandez, Masashi Hamaya

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

Comments Accepted at ICRA-2024

2404.18326 2024-04-30 cs.LG cs.AI 62%

SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies

Amir Samadi, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati

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

2404.16989 2024-04-29 cs.LG cs.AI cs.RO 62%

IDIL: Imitation Learning of Intent-Driven Expert Behavior

Sangwon Seo, Vaibhav Unhelkar

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

Comments Extended version of an identically-titled paper accepted at AAMAS 2024

2404.14552 2024-04-24 cs.LG cs.AI 62%

Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs

Lili Wu, Ben Evans, Riashat Islam, Raihan Seraj, Yonathan Efroni, Alex Lamb

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

2404.06971 2024-04-11 cs.CV cs.AI cs.LG 62%

TrajPRed: Trajectory Prediction with Region-based Relation Learning

Chen Zhou, Ghassan AlRegib, Armin Parchami, Kunjan Singh

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

2404.01636 2024-04-03 cs.CV cs.AI cs.LG cs.RO cs.SY eess.SY 62%

Learning to Control Camera Exposure via Reinforcement Learning

Kyunghyun Lee, Ukcheol Shin, Byeong-Uk Lee

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

Comments Accepted at CVPR 2024, *First two authors contributed equally to this work. Project page link: https://sites.google.com/view/drl-ae

2401.00104 2024-04-02 cs.LG cs.AI stat.ME 62%

Causal State Distillation for Explainable Reinforcement Learning

Wenhao Lu, Xufeng Zhao, Thilo Fryen, Jae Hee Lee, Mengdi Li, Sven Magg, Stefan Wermter

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

Comments https://lukaswill.github.io/; Accepted as oral by CLeaR 2024

2403.17542 2024-03-27 cs.LG cs.AI 62%

VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts

Marius Captari, Remo Sasso, Matthia Sabatelli

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

2403.15434 2024-03-26 cs.CL cs.AI 62%

ChatPattern: Layout Pattern Customization via Natural Language

Zixiao Wang, Yunheng Shen, Xufeng Yao, Wenqian Zhao, Yang Bai, Farzan Farnia, Bei Yu

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

Comments Accepted by DAC24

2403.07916 2024-03-14 cs.AI cs.LG 62%

Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization

Philip Ndikum, Serge Ndikum

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

2403.07548 2024-03-14 cs.AI cs.LG cs.RO 62%

Online Continual Learning For Interactive Instruction Following Agents

Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi

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

Comments ICLR 2024 (Project page: https://bhkim94.github.io/projects/CL-ALFRED)

1910.10266 2024-03-14 cs.LG cs.AI cs.SI stat.ML 62%

Recurrent Attention Walk for Semi-supervised Classification

Uchenna Akujuobi, Qiannan Zhang, Han Yufei, Xiangliang Zhang

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

Comments Accepted for WSDM 2020

2403.06993 2024-03-13 cs.RO cs.AI cs.LG cs.SY eess.IV eess.SY 62%

Automatic driving lane change safety prediction model based on LSTM

Wenjian Sun, Linying Pan, Jingyu Xu, Weixiang Wan, Yong Wang

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

2102.02649 2024-03-11 q-bio.GN cs.AI cs.LG 62%

A step toward a reinforcement learning de novo genome assembler

Kleber Padovani, Roberto Xavier, Rafael Cabral Borges, Andre Carvalho, Anna Reali, Annie Chateau, Ronnie Alves

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

2210.01282 2024-03-04 cs.LG cs.AI econ.EM stat.ML 62%

Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees

Siliang Zeng, Mingyi Hong, Alfredo Garcia

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

Comments This conference version of this paper refers to "Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees" in NeurIPS 2022

2402.04232 2024-02-08 cs.AI cs.CL 62%

Can Generative Agents Predict Emotion?

Ciaran Regan, Nanami Iwahashi, Shogo Tanaka, Mizuki Oka

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

Comments 14 pages, 6 figures

2310.07433 2024-02-08 cs.RO cs.AI cs.LG 62%

Imitation Learning from Observation with Automatic Discount Scheduling

Yuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao

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

Comments Accepted by ICLR 2024

2402.02904 2024-02-06 cs.RO cs.AI cs.LG 62%

Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows

Hao Yu, Zebin Huang, Qingbo Liu, Ignacio Carlucho, Mustafa Suphi Erden

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

Comments 8 pages, 5 figures; Submitted to WCCI-2024

2401.12819 2024-01-24 cs.LG cs.AI 62%

Dynamic Layer Tying for Parameter-Efficient Transformers

Tamir David Hay, Lior Wolf

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

2401.11459 2024-01-23 cs.AR cs.AI cs.LG 62%

AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology

Rongqing Cong, Wenyang He, Mingxuan Li, Bangning Luo, Zebin Yang, Yuchao Yang, Ru Huang, Bonan Yan

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

Comments for associated source codes, see https://bonany.cc/attentionleg

2401.00015 2024-01-02 cs.LG cs.AI cs.SY eess.SY 62%

Distributional Reinforcement Learning-based Energy Arbitrage Strategies in Imbalance Settlement Mechanism

Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder

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

2312.12781 2023-12-21 cs.LG cs.AI 62%

DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks

Mrinal Mathur, Sergey Plis

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

2312.12585 2023-12-21 cs.LG cs.AI cs.CR 62%

BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning

Jing Cui, Yufei Han, Yuzhe Ma, Jianbin Jiao, Junge Zhang

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 submission accepted by AAAI 2024. It is revised by integrating review comments

2205.00943 2023-12-20 cs.LG cs.AI cs.CV stat.ML 62%

CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning

Chenyu Sun, Hangwei Qian, Chunyan Miao

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

Comments Full paper with supplementary material, accepted by IJCAI 2022. Acknowledgements and affiliations are updated

2312.11118 2023-12-19 cs.AI cs.LG 62%

Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes

Yotam Amitai, Yael Septon, Ofra Amir

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

Comments Accepted to AAAI 2024

1. 记忆与上下文管理 4753 篇

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms

Intelligent Switching for Reset-Free RL

Deep Reinforcement Learning in Parameterized Action Space

EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networks

Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist

SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies

IDIL: Imitation Learning of Intent-Driven Expert Behavior

Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs

TrajPRed: Trajectory Prediction with Region-based Relation Learning

Learning to Control Camera Exposure via Reinforcement Learning

Causal State Distillation for Explainable Reinforcement Learning

VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts

ChatPattern: Layout Pattern Customization via Natural Language

Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization

Online Continual Learning For Interactive Instruction Following Agents

Recurrent Attention Walk for Semi-supervised Classification

Automatic driving lane change safety prediction model based on LSTM

A step toward a reinforcement learning de novo genome assembler

Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees

Can Generative Agents Predict Emotion?

Imitation Learning from Observation with Automatic Discount Scheduling

Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows

Dynamic Layer Tying for Parameter-Efficient Transformers

AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology

Distributional Reinforcement Learning-based Energy Arbitrage Strategies in Imbalance Settlement Mechanism

DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks

BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning

CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning

Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes