AI Agent - arXivDaily 专题

2209.12016 2023-05-26 cs.AI cs.LG 62%

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen, Alexandre Piché, Bart Dhoedt, Aaron Courville, Alexandre Lacoste

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

Comments Accepted at ICML 2023 (oral)

2305.14656 2023-05-25 cs.LG cs.AI cs.SC 62%

RSRM: Reinforcement Symbolic Regression Machine

Yilong Xu, Yang Liu, Hao Sun

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

Comments 18 pages

2305.14608 2023-05-25 cs.LG cs.AI 62%

Inverse Reinforcement Learning with the Average Reward Criterion

Feiyang Wu, Jingyang Ke, Anqi Wu

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

2305.13396 2023-05-24 cs.LG cs.AI 62%

Developmental Curiosity and Social Interaction in Virtual Agents

Chris Doyle, Sarah Shader, Michelle Lau, Megumi Sano, Daniel L. K. Yamins, Nick Haber

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

Comments 6 pages, 5 figures, 2 tables; accepted to CogSci 2023 with full paper publication in the proceedings

2305.12887 2023-05-23 eess.AS cs.AI cs.LG cs.SD 62%

ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding

Mireille Fares, Catherine Pelachaud, Nicolas Obin

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

Comments arXiv admin note: substantial text overlap with arXiv:2208.01917

2305.12782 2023-05-23 cs.CL cs.AI 62%

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, Kam-Fai Wong

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

Comments ACL 2023

2305.11107 2023-05-19 q-bio.NC cs.AI cs.LG cs.NE cs.RO 62%

From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning

Eugene R. Rush, Kaushik Jayaram, J. Sean Humbert

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

2107.08924 2023-05-19 cs.LG cs.AI stat.ML 62%

Epistemic Neural Networks

Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy

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

2305.09648 2023-05-17 cs.LG cs.AI 62%

Prompt-Tuning Decision Transformer with Preference Ranking

Shengchao Hu, Li Shen, Ya Zhang, Dacheng Tao

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

Comments 18 pages

2305.09600 2023-05-17 cs.AI cs.LG 62%

Deep Reinforcement Learning to Maximize Arterial Usage during Extreme Congestion

Ashutosh Dutta, Milan Jain, Arif Khan, Arun Sathanur

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

2305.02750 2023-05-10 cs.CL cs.AI 62%

A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects

Yang Deng, Wenqiang Lei, Wai Lam, Tat-Seng Chua

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

Comments Accepted by IJCAI 2023 Survey Track

2305.04727 2023-05-09 cs.LG cs.AI 62%

DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety

André Correia, Luís Alexandre

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

2305.04400 2023-05-09 cs.AI cs.CL q-bio.NC 62%

Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5

Gaurav Suri, Lily R. Slater, Ali Ziaee, Morgan Nguyen

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

2305.04361 2023-05-09 cs.LG cs.AI 62%

Truncating Trajectories in Monte Carlo Reinforcement Learning

Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli

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

2305.00597 2023-05-02 cs.RO cs.AI cs.LG 62%

Incremental procedural and sensorimotor learning in cognitive humanoid robots

Leonardo de Lellis Rossi, Leticia Mara Berto, Eric Rohmer, Paula Paro Costa, Ricardo Ribeiro Gudwin, Esther Luna Colombini, Alexandre da Silva Simoes

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

Comments Preprint submitted to IEEE Transactions on Cognitive and Developmental Systems

2304.13723 2023-04-27 cs.CV cs.AI cs.LG cs.RO 62%

A Control-Centric Benchmark for Video Prediction

Stephen Tian, Chelsea Finn, Jiajun Wu

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

Comments ICLR 2023

2304.13424 2023-04-27 cs.LG cs.AI cs.RO 62%

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

Li-Cheng Lan, Huan Zhang, Cho-Jui Hsieh

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

Comments ICRL 2023

2205.14557 2023-04-25 cs.LG cs.AI 62%

Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning

Qiang He, Huangyuan Su, Jieyu Zhang, Xinwen Hou

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

Comments Accepted to CVPR23. Website: https://sites.google.com/view/peer-cvpr2023/

2304.11052 2023-04-24 cs.CR cs.AI cs.LG 62%

A Multiagent CyberBattleSim for RL Cyber Operation Agents

Thomas Kunz, Christian Fisher, James La Novara-Gsell, Christopher Nguyen, Li Li

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

Comments To appear in Proceedings of the 2022 International Conference on Computational Science and Computational Intelligence

2304.10260 2023-04-21 cs.LG cs.AI cs.RO 62%

Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation

Edgardo Solano-Carrillo, Jannis Stoppe

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

Comments Code is available at https://github.com/DLR-MI/dati

2304.09821 2023-04-20 cs.CY cs.AI cs.HC cs.LG cs.LO 62%

Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems

Mark Abdelshiheed, John Wesley Hostetter, Tiffany Barnes, Min Chi

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

2112.05848 2023-04-19 cs.LG cs.AI 62%

Faster Deep Reinforcement Learning with Slower Online Network

Kavosh Asadi, Rasool Fakoor, Omer Gottesman, Taesup Kim, Michael L. Littman, Alexander J. Smola

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

Comments Published at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

2105.10266 2023-04-18 cs.RO cs.AI cs.LG 62%

Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving

Carl-Johan Hoel, Krister Wolff, Leo Laine

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

Journal ref Transactions on Intelligent Transportation Systems, 2023

2304.04782 2023-04-12 cs.LG cs.AI stat.ML 62%

Reinforcement Learning from Passive Data via Latent Intentions

Dibya Ghosh, Chethan Bhateja, Sergey Levine

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

Comments Accompanying website at https://dibyaghosh.com/icvf/

2304.03755 2023-04-10 math.OC cs.AI cs.LG 62%

Online Learning for Scheduling MIP Heuristics

Antonia Chmiela, Ambros Gleixner, Pawel Lichocki, Sebastian Pokutta

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

Comments Published in the Proceedings of CPAIOR 2023

2304.01244 2023-04-05 cs.LG cs.AI cs.CR 62%

Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents

Li Li, Jean-Pierre S. El Rami, Adrian Taylor, James Hailing Rao, Thomas Kunz

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

Comments To be published in the Proceedings of the 5th International Conference on Machine Learning for Networking (MLN'2022)

2303.17683 2023-04-03 cs.CL cs.AI 62%

Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages

Aarohi Srivastava, David Chiang

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

Comments Accepted for publication at VarDial 2023

2202.10324 2023-04-03 cs.CV cs.AI cs.LG cs.RO 62%

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

Che Wang, Xufang Luo, Keith Ross, Dongsheng Li

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

Comments 41 pages, camera-ready final version, accepted to NeurIPS 2022

2206.11736 2023-03-30 cs.CV cs.AI cs.LG 62%

NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds

Patrick Feeney, Sarah Schneider, Panagiotis Lymperopoulos, Li-Ping Liu, Matthias Scheutz, Michael C. Hughes

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

Comments Published in Transactions on Machine Learning Research (03/2023)

2106.10365 2023-03-30 cs.LG cs.AI 62%

Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments

Abdus Salam Azad, Edward Kim, Qiancheng Wu, Kimin Lee, Ion Stoica, Pieter Abbeel, Sanjit A. Seshia

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

Comments First two authors contributed equally. The final version of this paper is accepted at Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6028-6036. https://doi.org/10.1609/aaai.v36i6.20549

1. Agent评测 15801 篇

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

RSRM: Reinforcement Symbolic Regression Machine

Inverse Reinforcement Learning with the Average Reward Criterion

Developmental Curiosity and Social Interaction in Virtual Agents

ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning

Epistemic Neural Networks

Prompt-Tuning Decision Transformer with Preference Ranking

Deep Reinforcement Learning to Maximize Arterial Usage during Extreme Congestion

A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects

DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety

Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5

Truncating Trajectories in Monte Carlo Reinforcement Learning

Incremental procedural and sensorimotor learning in cognitive humanoid robots

A Control-Centric Benchmark for Video Prediction

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning

A Multiagent CyberBattleSim for RL Cyber Operation Agents

Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation

Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems

Faster Deep Reinforcement Learning with Slower Online Network

Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving

Reinforcement Learning from Passive Data via Latent Intentions

Online Learning for Scheduling MIP Heuristics

Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents

Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds

Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments