AI Agent - arXivDaily 专题

2205.00361 2022-05-03 cs.LG cs.AI cs.CR 62%

Combined Learning of Neural Network Weights for Privacy in Collaborative Tasks

Aline R. Ioste, Alan M. Durham, Marcelo Finger

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

2204.12935 2022-04-28 cs.CL cs.AI 62%

AdaCoach: A Virtual Coach for Training Customer Service Agents

Shuang Peng, Shuai Zhu, Minghui Yang, Haozhou Huang, Dan Liu, Zujie Wen, Xuelian Li, Biao Fan

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

Comments 5 pages

2204.11827 2022-04-26 cs.LG cs.AI cs.RO 62%

Task-Induced Representation Learning

Jun Yamada, Karl Pertsch, Anisha Gunjal, Joseph J. Lim

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

Comments International Conference on Learning Representations (ICLR), 2022

2201.00042 2022-04-26 cs.NE cs.AI cs.LG q-bio.NC 62%

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments

Abhiram Iyer, Karan Grewal, Akash Velu, Lucas Oliveira Souza, Jeremy Forest, Subutai Ahmad

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

Comments 31 pages, 17 figures

Journal ref Frontiers in Neurorobotics 16 2022 (1-23)

2204.09597 2022-04-22 cs.CL cs.AI 62%

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games

Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Joey Tianyi Zhou, Chengqi Zhang

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

Comments ACL2022, fix some typos

2204.08957 2022-04-20 cs.LG cs.AI 62%

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Jongmin Lee, Cosmin Paduraru, Daniel J. Mankowitz, Nicolas Heess, Doina Precup, Kee-Eung Kim, Arthur Guez

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

Comments 24 pages, 6 figures, Accepted at ICLR 2022 (spotlight)

2204.02785 2022-04-07 cs.AI cs.LG 62%

Reinforcement Learning Agents in Colonel Blotto

Joseph Christian G. Noel

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

2102.11492 2022-04-06 cs.LG cs.AI cs.SY eess.SY 62%

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

Xianyuan Zhan, Haoran Xu, Yue Zhang, Xiangyu Zhu, Honglei Yin, Yu Zheng

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

Journal ref Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI2022)

2203.16777 2022-04-01 cs.CV cs.AI cs.LG 62%

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Yang Shao, Quan Kong, Tadayuki Matsumura, Taiki Fuji, Kiyoto Ito, Hiroyuki Mizuno

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

2202.13657 2022-03-25 cs.LG cs.AI cs.CV 62%

Avalanche RL: a Continual Reinforcement Learning Library

Nicolò Lucchesi, Antonio Carta, Vincenzo Lomonaco, Davide Bacciu

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

Comments Presented at the 21st International Conference on Image Analysis and Processing (ICIAP 2021)

2203.11889 2022-03-23 cs.LG cs.AI cs.NE cs.SC stat.ML 62%

Insights From the NeurIPS 2021 NetHack Challenge

Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, Daejin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich Küttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim Rocktäschel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, Michał Sypetkowski

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

Comments Under review at PMLR for the NeuRIPS 2021 Competition Workshop Track, 10 pages + 10 in appendices

2111.13485 2022-03-18 cs.LG cs.AI stat.ML 62%

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

Zhizhou Ren, Ruihan Guo, Yuan Zhou, Jian Peng

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

Comments Tenth International Conference on Learning Representations (ICLR 2022 Spotlight)

2109.04504 2022-03-17 cs.LG cs.AI stat.ML 62%

Bootstrapped Meta-Learning

Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver, Satinder Singh

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

Comments Published at ICLR 2022. 37 pages, 19 figures, 9 tables

2106.02193 2022-03-17 cs.LG cs.AI 62%

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

Bogdan Mazoure, Ahmed M. Ahmed, Patrick MacAlpine, R Devon Hjelm, Andrey Kolobov

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

Comments ICLR 2022

2203.02986 2022-03-08 cs.CV cs.AI cs.CL 62%

Modeling Coreference Relations in Visual Dialog

Mingxiao Li, Marie-Francine Moens

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

2008.05938 2022-03-07 cs.CV cs.LG cs.SE 62%

RGB cameras failures and their effects in autonomous driving applications

Francesco Secci, Andrea Ceccarelli

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

Comments submitted

2203.01810 2022-03-04 cs.LG cs.AI 62%

Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images

Bang You, Oleg Arenz, Youping Chen, Jan Peters

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

Comments 28 pages, 11 figures, 5 tables

Journal ref Neurocomputing 476(2022)102-114

2110.03262 2022-02-28 cs.CL cs.AI 62%

Situated Dialogue Learning through Procedural Environment Generation

Prithviraj Ammanabrolu, Renee Jia, Mark O. Riedl

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

Comments Camera ready. In proceedings of ACL 2022

2202.10630 2022-02-23 cs.LG cs.AI cs.CR 62%

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach

Yizhou Yang, Xin Liu

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

Comments 6 pages,4 Figures

2107.05431 2022-02-23 cs.LG cs.AI 62%

CoBERL: Contrastive BERT for Reinforcement Learning

Andrea Banino, Adrià Puidomenech Badia, Jacob Walker, Tim Scholtes, Jovana Mitrovic, Charles Blundell

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

Comments 9 pages, 2 figures, 6 tables

1912.03802 2022-02-17 cs.LG cs.AI stat.ML 62%

Group Fairness in Bandit Arm Selection

Candice Schumann, Zhi Lang, Nicholas Mattei, John P. Dickerson

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

Comments Accepted to AAMAS 2022

2102.11938 2022-02-16 cs.AI cs.LG 62%

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

Kanishk Gandhi, Gala Stojnic, Brenden M. Lake, Moira R. Dillon

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

Comments Published in Advances in Neural Information Processing Systems (NeurIPS) 34

2201.03544 2022-02-15 cs.LG cs.AI stat.ML 62%

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Alexander Pan, Kush Bhatia, Jacob Steinhardt

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

Comments ICLR 2022; 19 pages

2010.02193 2022-02-15 cs.LG cs.AI stat.ML 62%

Mastering Atari with Discrete World Models

Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba

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

Comments Published at ICLR 2021. Website: https://danijar.com/dreamerv2

2202.01949 2022-02-07 cs.NI cs.AI cs.LG 62%

A Reinforcement Learning Framework for PQoS in a Teleoperated Driving Scenario

Federico Mason, Matteo Drago, Tommaso Zugno, Marco Giordani, Mate Boban, Michele Zorzi

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

Comments 6 pages, 5 figures, 2 tables. The paper has been submitted to IEEE WCNC 2022. Copyright may change without notice

2201.13226 2022-02-01 cs.CY cs.AI cs.LG 62%

Online Assessment Misconduct Detection using Internet Protocol and Behavioural Classification

Leslie Ching Ow Tiong, HeeJeong Jasmine Lee, Kai Li Lim

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

2201.10422 2022-01-26 cs.CL cs.AI 62%

Language Generation for Broad-Coverage, Explainable Cognitive Systems

Marjorie McShane, Ivan Leon

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

Comments Presented at The Ninth Advances in Cognitive Systems (ACS) Conference 2021 (arXiv:2201.06134)

2102.09677 2022-01-26 cs.LG cs.AI cs.NE cs.RO cs.SY eess.SY 62%

Training a Resilient Q-Network against Observational Interference

Chao-Han Huck Yang, I-Te Danny Hung, Yi Ouyang, Pin-Yu Chen

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

Comments Accepted to AAAI 2022. 9 pages

2201.09708 2022-01-25 cs.AI cs.CL 62%

Towards Collaborative Question Answering: A Preliminary Study

Xiangkun Hu, Hang Yan, Qipeng Guo, Xipeng Qiu, Weinan Zhang, Zheng Zhang

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

2201.08896 2022-01-25 cs.LG cs.AI 62%

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, Aleksandra Faust

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

Comments Published in NeurIPS 2021

1. Agent评测 15801 篇

Combined Learning of Neural Network Weights for Privacy in Collaborative Tasks

AdaCoach: A Virtual Coach for Training Customer Service Agents

Task-Induced Representation Learning

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Reinforcement Learning Agents in Colonel Blotto

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Avalanche RL: a Continual Reinforcement Learning Library

Insights From the NeurIPS 2021 NetHack Challenge

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

Bootstrapped Meta-Learning

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

Modeling Coreference Relations in Visual Dialog

RGB cameras failures and their effects in autonomous driving applications

Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images

Situated Dialogue Learning through Procedural Environment Generation

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach

CoBERL: Contrastive BERT for Reinforcement Learning

Group Fairness in Bandit Arm Selection

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Mastering Atari with Discrete World Models

A Reinforcement Learning Framework for PQoS in a Teleoperated Driving Scenario

Online Assessment Misconduct Detection using Internet Protocol and Behavioural Classification

Language Generation for Broad-Coverage, Explainable Cognitive Systems

Training a Resilient Q-Network against Observational Interference

Towards Collaborative Question Answering: A Preliminary Study

Environment Generation for Zero-Shot Compositional Reinforcement Learning