AI Agent - arXivDaily 专题

2309.09476 2023-10-06 cs.AI cs.LG 73%

Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules

Johor Jara Gonzalez, Seth Cooper, Matthew Guzdial

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

Comments 10 pages, 6 figures, Artificial Intelligence and Interactive Digital Entertainment

2308.04905 2023-08-10 cs.NI cs.AI cs.LG cs.MA 73%

GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters

Guillermo Bernárdez, José Suárez-Varela, Xiang Shi, Shihan Xiao, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio

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

Comments 11 pages, 7 figures, 2 tables

2304.03442 2023-08-08 cs.HC cs.AI cs.LG 73%

Generative Agents: Interactive Simulacra of Human Behavior

Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein

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

2210.14891 2023-07-25 cs.LG cs.AI 73%

Broken Neural Scaling Laws

Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger

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

Comments Published as a conference paper at International Conference on Learning Representations (ICLR) 2023

Journal ref International Conference on Learning Representations (ICLR), 2023

2307.07529 2023-07-18 cs.LG cs.AI cs.MA 73%

Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints

Jaeyeon Jang, Diego Klabjan, Han Liu, Nital S. Patel, Xiuqi Li, Balakrishnan Ananthanarayanan, Husam Dauod, Tzung-Han Juang

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

2207.10553 2023-07-04 cs.LG cs.AI cs.CV cs.MA 73%

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

Jennifer J. Sun, Markus Marks, Andrew Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Sebastian Oleszko, Zachary Partridge, Milan Peelman, Alice Robie, Catherine E. Schretter, Keith Sheppard, Chao Sun, Param Uttarwar, Julian M. Wagner, Eric Werner, Joseph Parker, Pietro Perona, Yisong Yue, Kristin Branson, Ann Kennedy

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

Comments To appear in ICML 2023, Project website: https://sites.google.com/view/computational-behavior/our-datasets/mabe2022-dataset

2305.09064 2023-05-17 cs.LG cs.AI cs.HC 73%

Capturing Humans' Mental Models of AI: An Item Response Theory Approach

Markelle Kelly, Aakriti Kumar, Padhraic Smyth, Mark Steyvers

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

Comments FAccT 2023

2112.14602 2023-04-14 cs.RO cs.AI cs.LG 73%

Modified DDPG car-following model with a real-world human driving experience with CARLA simulator

Dianzhao Li, Ostap Okhrin

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

2112.02807 2023-04-13 cs.SE cs.LG 73%

MDPFuzz: Testing Models Solving Markov Decision Processes

Qi Pang, Yuanyuan Yuan, Shuai Wang

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

2303.13360 2023-03-24 cs.CL cs.LG 73%

Towards the Scalable Evaluation of Cooperativeness in Language Models

Alan Chan, Maxime Riché, Jesse Clifton

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

2302.14604 2023-03-07 cs.MA cs.AI cs.GT cs.LG 73%

IQ-Flow: Mechanism Design for Inducing Cooperative Behavior to Self-Interested Agents in Sequential Social Dilemmas

Bengisu Guresti, Abdullah Vanlioglu, Nazim Kemal Ure

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

Comments AAMAS 2023

2211.10445 2023-03-03 cs.LG cs.AI 73%

Building a Subspace of Policies for Scalable Continual Learning

Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu

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

Comments Accepted at ICLR2023 (notable-top-25%). website: https://continual-subspace-policies-streamlit-app-gofujp.streamlit.app/ code: https://github.com/facebookresearch/salina/tree/main/salina_cl

2301.11892 2023-01-30 cs.LG cs.AI cs.CV 73%

Streaming LifeLong Learning With Any-Time Inference

Soumya Banerjee, Vinay Kumar Verma, Vinay P. Namboodiri

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

Comments arXiv admin note: substantial text overlap with arXiv:2110.10741

2301.00637 2023-01-03 cs.GT cs.AI cs.LG cs.MA 73%

Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach

Yuli. Zhang, Shangbo. Wang, Ruiyuan. Jiang

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

Comments 7 pages,7 figures

2110.05437 2022-11-29 cs.RO cs.AI cs.LG cs.NE 73%

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture

Chinmay Vilas Samak, Tanmay Vilas Samak, Sivanathan Kandhasamy

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

2211.11513 2022-11-22 q-fin.ST cs.AI cs.LG 73%

DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift

Defu Cao, Yousef El-Laham, Loc Trinh, Svitlana Vyetrenko, Yan Liu

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

Comments 11 pages, 5 figures, already accepted by NeurIPS 2022 Distribution Shifts Workshop

2211.05500 2022-11-11 cs.LG cs.AI 73%

Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

Patrik Hammersborg, Inga Strümke

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

Comments For associated code, see https://github.com/patrik-ha/explainable-minichess

2211.02545 2022-11-10 cs.RO cs.AI cs.CV cs.LG cs.MA 73%

GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting

Alexander Cui, Sergio Casas, Kelvin Wong, Simon Suo, Raquel Urtasun

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

2210.10595 2022-10-20 cs.LG cs.AI 73%

DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

Alessandro Palmas

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

Comments 14 pages, 7 figures

2206.04199 2022-10-13 cs.AI cs.LG cs.NE 73%

Deep Surrogate Assisted Generation of Environments

Varun Bhatt, Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis

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

Comments 26 pages, 15 figures, supplemental website at https://dsagepaper.github.io/

2206.08686 2022-10-12 cs.RO cs.AI cs.LG cs.MA 73%

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang

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

Comments 38 pages, 8 figures

2106.10566 2022-10-04 cs.LG cs.AI 73%

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao

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

Comments 8 pages, 6 figures

2209.10485 2022-09-22 cs.LG cs.AI cs.GL cs.MA 73%

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius

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

Comments Published at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). Website: see https://sites.google.com/view/marl-standard-protocol . 43 Pages, 21 Figures, 8 Tables

2208.04832 2022-08-10 cs.AI cs.LG cs.NE 73%

On the Importance of Critical Period in Multi-stage Reinforcement Learning

Junseok Park, Inwoo Hwang, Min Whoo Lee, Hyunseok Oh, Minsu Lee, Youngki Lee, Byoung-Tak Zhang

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

Comments Accepted by the ICML Complex Feedback in Online Learning Workshop (Open Problems) 2022

2207.12322 2022-07-26 cs.AI cs.LG 73%

Self-Explaining Deviations for Coordination

Hengyuan Hu, Samuel Sokota, David Wu, Anton Bakhtin, Andrei Lupu, Brandon Cui, Jakob N. Foerster

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

2205.05739 2022-07-19 cs.CV cs.AI cs.CL cs.HC cs.MA 73%

Learning to Retrieve Videos by Asking Questions

Avinash Madasu, Junier Oliva, Gedas Bertasius

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

Journal ref ACM Multimedia 2022

2206.03970 2022-06-13 cs.CV cs.AI cs.LG cs.RO 73%

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

DiJia Su, Bertrand Douillard, Rami Al-Rfou, Cheolho Park, Benjamin Sapp

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

Comments Accepted at ICRA 2022

2206.03348 2022-06-08 cs.GT cs.AI cs.LG 73%

Specification-Guided Learning of Nash Equilibria with High Social Welfare

Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur

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

2205.02953 2022-05-11 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 73%

Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing

Jonathan Francis, Bingqing Chen, Siddha Ganju, Sidharth Kathpal, Jyotish Poonganam, Ayush Shivani, Vrushank Vyas, Sahika Genc, Ivan Zhukov, Max Kumskoy, Anirudh Koul, Jean Oh, Eric Nyberg

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

Comments 20 pages, 4 figures, 2 tables

2109.07703 2022-05-02 cs.RO cs.AI cs.CV cs.LG 73%

ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI

Guanxiong Chen, Haoyu Yang, Ian M. Mitchell

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

Comments Camera-ready version submitted to Canadian Conference on Computer and Robot Vision (CRV) 2022

1. Agent评测 15756 篇

Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules

GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters

Generative Agents: Interactive Simulacra of Human Behavior

Broken Neural Scaling Laws

Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

Capturing Humans' Mental Models of AI: An Item Response Theory Approach

Modified DDPG car-following model with a real-world human driving experience with CARLA simulator

MDPFuzz: Testing Models Solving Markov Decision Processes

Towards the Scalable Evaluation of Cooperativeness in Language Models

IQ-Flow: Mechanism Design for Inducing Cooperative Behavior to Self-Interested Agents in Sequential Social Dilemmas

Building a Subspace of Policies for Scalable Continual Learning

Streaming LifeLong Learning With Any-Time Inference

Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture

DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift

Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting

DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

Deep Surrogate Assisted Generation of Environments

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

On the Importance of Critical Period in Multi-stage Reinforcement Learning

Self-Explaining Deviations for Coordination

Learning to Retrieve Videos by Asking Questions

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

Specification-Guided Learning of Nash Equilibria with High Social Welfare

Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing

ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI