AI Agent - arXivDaily 专题

2310.06835 2023-10-17 cs.LG cs.AI cs.LO 62%

Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning

Kaustuv Mukherji, Devendra Parkar, Lahari Pokala, Dyuman Aditya, Paulo Shakarian, Clark Dorman

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Submitted to 2024 IEEE International Conference on Semantic Computing

2310.01957 2023-10-17 cs.RO cs.AI cs.CL cs.CV 62%

Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving

Long Chen, Oleg Sinavski, Jan Hünermann, Alice Karnsund, Andrew James Willmott, Danny Birch, Daniel Maund, Jamie Shotton

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

2310.08185 2023-10-13 cs.CL cs.AI 62%

EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation

Wang You, Wenshan Wu, Yaobo Liang, Shaoguang Mao, Chenfei Wu, Maosong Cao, Yuzhe Cai, Yiduo Guo, Yan Xia, Furu Wei, Nan Duan

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.CL

2310.06983 2023-10-12 cs.CL cs.LG 62%

Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models

Courtland Leer, Vincent Trost, Vineeth Voruganti

专题命中 Agent评测：agent(abstract)；分类 cs.CL、cs.LG

2310.06245 2023-10-11 cs.AI cs.CL 62%

We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses

Benjamin Kane, Lenhart Schubert

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

2310.04373 2023-10-11 cs.LG cs.AI 62%

Confronting Reward Model Overoptimization with Constrained RLHF

Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2310.05871 2023-10-10 cs.AI cs.LG cs.SY eess.SY 62%

Dynamic value alignment through preference aggregation of multiple objectives

Marcin Korecki, Damian Dailisan, Cesare Carissimo

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2310.04467 2023-10-10 cs.LG cs.AI cs.SY eess.SY 62%

Design Principles for Lifelong Learning AI Accelerators

Dhireesha Kudithipudi, Anurag Daram, Abdullah M. Zyarah, Fatima Tuz Zohora, James B. Aimone, Angel Yanguas-Gil, Nicholas Soures, Emre Neftci, Matthew Mattina, Vincenzo Lomonaco, Clare D. Thiem, Benjamin Epstein

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2310.03161 2023-10-06 cs.LG cs.AI 62%

Neural architecture impact on identifying temporally extended Reinforcement Learning tasks

Victor Vadakechirayath George

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Master's thesis at Albert-Ludwigs-University, Freiburg Faculty of Engineering, Department of Computer Science Chair for Machine Learning. Advisor: Raghu Rajan, Examiners: Prof. Dr. Frank Hutter, Prof. Dr. Thomas Brox

2309.01807 2023-10-06 cs.LG cs.AI cs.RO 62%

Marginalized Importance Sampling for Off-Environment Policy Evaluation

Pulkit Katdare, Nan Jiang, Katherine Driggs-Campbell

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2305.15555 2023-10-05 cs.LG cs.AI 62%

Deep Reinforcement Learning with Plasticity Injection

Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2023 camera-ready

2310.00166 2023-10-03 cs.AI cs.LG 62%

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

Martin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments The first two authors equally contributed - order decided by coin flip

2310.00010 2023-10-03 cs.RO cs.AI cs.LG 62%

Artificial Empathy Classification: A Survey of Deep Learning Techniques, Datasets, and Evaluation Scales

Sharjeel Tahir, Syed Afaq Shah, Jumana Abu-Khalaf

专题命中 Agent评测：workflow(abstract)；分类 cs.AI、cs.LG

2306.05032 2023-10-03 cs.SE cs.LG 62%

Log-based Anomaly Detection based on EVT Theory with feedback

Jinyang Liu, Junjie Huang, Yintong Huo, Zhihan Jiang, Jiazhen Gu, Zhuangbin Chen, Cong Feng, Minzhi Yan, Michael R. Lyu

专题命中 Agent评测：agent(abstract)；分类 cs.LG、cs.SE

2302.02506 2023-10-02 cs.LG cs.AI 62%

Generating Dispatching Rules for the Interrupting Swap-Allowed Blocking Job Shop Problem Using Graph Neural Network and Reinforcement Learning

Vivian W. H. Wong, Sang Hun Kim, Junyoung Park, Jinkyoo Park, Kincho H. Law

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, 10 figures. Supplementary Material not included

2111.01919 2023-09-28 cs.LG cs.AI cs.NE cs.RO 62%

Discovering and Exploiting Sparse Rewards in a Learned Behavior Space

Giuseppe Paolo, Miranda Coninx, Alban Laflaquière, Stephane Doncieux

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 25 pages. Published by the Evolutionary Computation Journal, MIT Press

2309.14395 2023-09-27 cs.LG cs.AI 62%

Implicit Sensing in Traffic Optimization: Advanced Deep Reinforcement Learning Techniques

Emanuel Figetakis, Yahuza Bello, Ahmed Refaey, Lei Lei, Medhat Moussa

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2309.12295 2023-09-26 cs.CV cs.AI cs.LG cs.RO 62%

Learning to Drive Anywhere

Ruizhao Zhu, Peng Huang, Eshed Ohn-Bar, Venkatesh Saligrama

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Conference on Robot Learning (CoRL) 2023

2309.11307 2023-09-21 cs.CL cs.AI 62%

Rating Prediction in Conversational Task Assistants with Behavioral and Conversational-Flow Features

Rafael Ferreira, David Semedo, João Magalhães

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

2309.10175 2023-09-20 cs.RO cs.AI cs.LG 62%

One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers

Abraham George, Amir Barati Farimani

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 6 figures

2304.04321 2023-09-12 cs.AI cs.CL cs.CV cs.RO 62%

ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes

Ran Gong, Jiangyong Huang, Yizhou Zhao, Haoran Geng, Xiaofeng Gao, Qingyang Wu, Wensi Ai, Ziheng Zhou, Demetri Terzopoulos, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.CL

Comments The first two authors contributed equally; 20 pages; 17 figures; project availalbe: https://arnold-benchmark.github.io/ ICCV 2023

2308.15097 2023-08-30 cs.AI cs.CL 62%

Sequential annotations for naturally-occurring HRI: first insights

Lucien Tisserand, Frédéric Armetta, Heike Baldauf-Quilliatre, Antoine Bouquin, Salima Hassas, Mathieu Lefort

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

Comments Peer-reviewed workshop paper accepted for the ''Human-Robot Conversational Interaction'' workshop that took place at the ''ACM/IEEE International Conference on Human-Robot Interaction'' 2023 Conference in Stockholm, Sweden

2308.13289 2023-08-28 q-fin.TR cs.AI cs.CE cs.LG 62%

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Sascha Frey, Kang Li, Peer Nagy, Silvia Sapora, Chris Lu, Stefan Zohren, Jakob Foerster, Anisoara Calinescu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2308.07352 2023-08-16 cs.LG cs.AI physics.comp-ph physics.flu-dyn 62%

Bayesian Physics-Informed Neural Network for the Forward and Inverse Simulation of Engineered Nano-particles Mobility in a Contaminated Aquifer

Shikhar Nilabh, Fidel Grandia

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments To be submitted to a NeurIPS 2023 workshop. arXiv admin note: substantial text overlap with arXiv:2211.03525

2308.07329 2023-08-16 cs.AI cs.LG q-fin.TR 62%

Variations on the Reinforcement Learning performance of Blackjack

Avish Buramdoyal, Tim Gebbie

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 15 figures, 7 tables

2308.01274 2023-08-03 cs.CR cs.AI cs.LG cs.MA cs.RO 62%

BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems

Md Tamjid Hossain, Hung Manh La, Shahriar Badsha, Anton Netchaev

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 6 figures, 3 tables, Accepted for publication in the proceeding of The 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), Oct 01-05, 2023, Detroit, Michigan, USA

2308.01207 2023-08-03 cs.NE cs.AI cs.LG 62%

BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization

Junyi Wang, Yuanyang Zhu, Zhi Wang, Yan Zheng, Jianye Hao, Chunlin Chen

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Published as a conference paper at European Conference on Artificial Intelligence (ECAI) 2023

2305.00365 2023-08-03 cs.LG cs.AI cs.SY eess.SY 62%

A Transfer Learning Approach to Minimize Reinforcement Learning Risks in Energy Optimization for Smart Buildings

Mikhail Genkin, J. J. McArthur

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 31 pages, 9 figures, submitted to the journal Energy and Buildings

2307.13447 2023-07-26 cs.RO cs.AI cs.LG 62%

A behavioural transformer for effective collaboration between a robot and a non-stationary human

Ruaridh Mon-Williams, Theodoros Stouraitis, Sethu Vijayakumar

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 6 figures

2302.02119 2023-07-26 cs.AI cs.LG 62%

Diversity Induced Environment Design via Self-Play

Dexun Li, Wenjun Li, Pradeep Varakantham

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

1. Agent评测 15756 篇

Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning

Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving

EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation

Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models

We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses

Confronting Reward Model Overoptimization with Constrained RLHF

Dynamic value alignment through preference aggregation of multiple objectives

Design Principles for Lifelong Learning AI Accelerators

Neural architecture impact on identifying temporally extended Reinforcement Learning tasks

Marginalized Importance Sampling for Off-Environment Policy Evaluation

Deep Reinforcement Learning with Plasticity Injection

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

Artificial Empathy Classification: A Survey of Deep Learning Techniques, Datasets, and Evaluation Scales

Log-based Anomaly Detection based on EVT Theory with feedback

Generating Dispatching Rules for the Interrupting Swap-Allowed Blocking Job Shop Problem Using Graph Neural Network and Reinforcement Learning

Discovering and Exploiting Sparse Rewards in a Learned Behavior Space

Implicit Sensing in Traffic Optimization: Advanced Deep Reinforcement Learning Techniques

Learning to Drive Anywhere

Rating Prediction in Conversational Task Assistants with Behavioral and Conversational-Flow Features

One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers

ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes

Sequential annotations for naturally-occurring HRI: first insights

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Bayesian Physics-Informed Neural Network for the Forward and Inverse Simulation of Engineered Nano-particles Mobility in a Contaminated Aquifer

Variations on the Reinforcement Learning performance of Blackjack

BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems

BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization

A Transfer Learning Approach to Minimize Reinforcement Learning Risks in Energy Optimization for Smart Buildings

A behavioural transformer for effective collaboration between a robot and a non-stationary human

Diversity Induced Environment Design via Self-Play