AI Agent - arXivDaily 专题

2002.05630 2021-02-01 cs.AI cs.LG stat.ML 62%

On the Sensory Commutativity of Action Sequences for Embodied Agents

Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat

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

Comments Accepted to RSS'20 Workshop on Self-Supervised Robot Learning & to the Workshop on Learning in Artificial Open Worlds at ICML20 & Extended abstract at AAMAS21

1906.09323 2021-01-29 cs.LG cs.AI cs.GT stat.ML 62%

Reinforcement Learning with Convex Constraints

Sobhan Miryoosefi, Kianté Brantley, Hal Daumé, Miroslav Dudik, Robert Schapire

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

Journal ref Advances in Neural Information Processing Systems 32 (2019), 14093-14102

2010.02809 2021-01-26 cs.LG cs.AI 62%

Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review

Yuqi Si, Jingcheng Du, Zhao Li, Xiaoqian Jiang, Timothy Miller, Fei Wang, W. Jim Zheng, Kirk Roberts

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

2006.07185 2021-01-26 cs.AI cs.LG stat.ML 62%

Grounding Language to Autonomously-Acquired Skills via Goal Generation

Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud

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

Comments Published at ICLR 2021

2003.05856 2021-01-22 cs.AI cs.LG 62%

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin

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

Journal ref NeurIPS 2020

2101.03431 2021-01-12 cs.AI cs.CL cs.CV cs.RO 62%

Are We There Yet? Learning to Localize in Embodied Instruction Following

Shane Storks, Qiaozi Gao, Govind Thattai, Gokhan Tur

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

Comments Accepted to HAI @ AAAI 2021

2007.10527 2021-01-06 cs.LG cs.AI stat.ML 62%

Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks

Sachin Ravi, Sebastian Musslick, Maia Hamin, Theodore L. Willke, Jonathan D. Cohen

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

2012.13483 2020-12-29 cs.LG cs.AI 62%

Whom to Test? Active Sampling Strategies for Managing COVID-19

Yingfei Wang, Inbal Yahav, Balaji Padmanabhan

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

2011.06464 2020-12-29 cs.RO cs.AI cs.CV cs.LG 62%

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators

Hsiao-Yu Fish Tung, Zhou Xian, Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki

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

2004.09846 2020-12-22 cs.LG cs.AI stat.ML 62%

SIBRE: Self Improvement Based REwards for Adaptive Feedback in Reinforcement Learning

Somjit Nath, Richa Verma, Abhik Ray, Harshad Khadilkar

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

Comments 7 pages, 10 figures

2012.08920 2020-12-17 cs.CL cs.AI 62%

R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching

Kun Zhang, Le Wu, Guangyi Lv, Meng Wang, Enhong Chen, Shulan Ruan

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

Comments This paper has been accepted to/by AAAI2021

2012.08858 2020-12-17 cs.AI cs.LG cs.MA cs.NE 62%

Lévy walks derived from a Bayesian decision-making model in non-stationary environments

Shuji Shinohara, Nobuhito Manome, Yoshihiro Nakajima, Yukio Pegio Gunji, Toru Moriyama, Hiroshi Okamoto, Shunji Mitsuyoshi, Ung-il Chung

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

2011.13093 2020-11-30 cs.LG cs.AI 62%

Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning

Sanghwa Lee, Jaeyoung Lee, Ichiro Hasuo

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

Comments Presented at Deep Reinforcement Learning Workshop, NeurIPS 2020

2011.06709 2020-11-26 cs.LG cs.AI stat.ML 62%

Active Reinforcement Learning: Observing Rewards at a Cost

David Krueger, Jan Leike, Owain Evans, John Salvatier

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

Comments Originally appeared at the NeurIPS 2016 "Future of Interactive Learning Machines (FILM)" workshop

1907.04543 2020-11-25 cs.LG cs.AI stat.ML 62%

An Optimistic Perspective on Offline Reinforcement Learning

Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi

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

Comments ICML 2020. An earlier version was titled "Striving for Simplicity in Off-Policy Deep Reinforcement Learning". Project Website: https://offline-rl.github.io

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:104-114, 2020

2011.09264 2020-11-20 cs.LG cs.AI 62%

Inverse Reinforcement Learning via Matching of Optimality Profiles

Luis Haug, Ivan Ovinnikov, Eugene Bykovets

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

2011.09294 2020-11-19 cs.AI cs.LG 62%

Using Unity to Help Solve Intelligence

Tom Ward, Andrew Bolt, Nik Hemmings, Simon Carter, Manuel Sanchez, Ricardo Barreira, Seb Noury, Keith Anderson, Jay Lemmon, Jonathan Coe, Piotr Trochim, Tom Handley, Adrian Bolton

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

1805.09267 2020-11-19 cs.LG cs.AI stat.ML 62%

Reinforcement Learning for Heterogeneous Teams with PALO Bounds

Roi Ceren, Prashant Doshi, Keyang He

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

Journal ref Neurocomputing, Volume 420, 8 January 2021, Pages 36-56

2011.08827 2020-11-18 cs.LG cs.AI 62%

Avoiding Tampering Incentives in Deep RL via Decoupled Approval

Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg

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

2004.14307 2020-11-17 cs.CL cs.LG 62%

UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues

Hung Le, Doyen Sahoo, Chenghao Liu, Nancy F. Chen, Steven C. H. Hoi

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

Comments Accepted The 2020 Conference on Empirical Methods in Natural Language Processing

1910.11914 2020-11-13 cs.LG cs.AI quant-ph stat.ML 62%

On the convergence of projective-simulation-based reinforcement learning in Markov decision processes

Walter L. Boyajian, Jens Clausen, Lea M. Trenkwalder, Vedran Dunjko, Hans J. Briegel

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

Comments 20 pages, 2 figures, v3: a few minor updates to match journal version. Order of authors changed

Journal ref Quantum Mach. Intell. 2, 13 (2020)

2011.05286 2020-11-11 cs.LG cs.AI 62%

Continual Learning of Control Primitives: Skill Discovery via Reset-Games

Kelvin Xu, Siddharth Verma, Chelsea Finn, Sergey Levine

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

Comments To appear at NeurIPS 2020

2011.01975 2020-11-05 cs.AI cs.CV cs.LG cs.RO 62%

Rearrangement: A Challenge for Embodied AI

Dhruv Batra, Angel X. Chang, Sonia Chernova, Andrew J. Davison, Jia Deng, Vladlen Koltun, Sergey Levine, Jitendra Malik, Igor Mordatch, Roozbeh Mottaghi, Manolis Savva, Hao Su

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

Comments Authors are listed in alphabetical order

2001.00805 2020-11-05 cs.LG cs.AI 62%

Making Sense of Reinforcement Learning and Probabilistic Inference

Brendan O'Donoghue, Ian Osband, Catalin Ionescu

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

Comments ICLR 2020

2010.15469 2020-10-30 cs.LG cs.AI cs.RO 62%

Emergence of Spatial Coordinates via Exploration

Alban Laflaquière

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

Comments 4 pages, 2 figures, BabyMind Workshop at NeurIPS 2020

2010.13839 2020-10-28 cs.LG cs.CL 62%

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula, Michiaki Tatsubori

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

Comments Code is available at http://ibm.biz/VisualHints

2010.12639 2020-10-27 cs.RO cs.AI cs.CL cs.CV 62%

The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation

Shurjo Banerjee, Jesse Thomason, Jason J. Corso

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

Comments Conference on Robot Learning 2020

2010.10560 2020-10-22 cs.LG cs.AI cs.CY 62%

Reinforcement Learning for Optimization of COVID-19 Mitigation policies

Varun Kompella, Roberto Capobianco, Stacy Jong, Jonathan Browne, Spencer Fox, Lauren Meyers, Peter Wurman, Peter Stone

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

Comments *Joint First Authors

2002.10221 2020-10-21 cs.LG cs.AI 62%

The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI

Samuel Allen Alexander

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

Comments 16 pages

Journal ref Journal of Artificial General Intelligence 11(1): 70--85 (2020)

2010.09473 2020-10-20 cs.LG cs.AI 62%

Double-Linear Thompson Sampling for Context-Attentive Bandits

Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay, Yasaman Khazaeni, Irina Rish

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

Comments arXiv admin note: text overlap with arXiv:1906.09384

1. Agent评测 15801 篇

On the Sensory Commutativity of Action Sequences for Embodied Agents

Reinforcement Learning with Convex Constraints

Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review

Grounding Language to Autonomously-Acquired Skills via Goal Generation

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

Are We There Yet? Learning to Localize in Embodied Instruction Following

Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks

Whom to Test? Active Sampling Strategies for Managing COVID-19

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators

SIBRE: Self Improvement Based REwards for Adaptive Feedback in Reinforcement Learning

R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching

Lévy walks derived from a Bayesian decision-making model in non-stationary environments

Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning

Active Reinforcement Learning: Observing Rewards at a Cost

An Optimistic Perspective on Offline Reinforcement Learning

Inverse Reinforcement Learning via Matching of Optimality Profiles

Using Unity to Help Solve Intelligence

Reinforcement Learning for Heterogeneous Teams with PALO Bounds

Avoiding Tampering Incentives in Deep RL via Decoupled Approval

UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues

On the convergence of projective-simulation-based reinforcement learning in Markov decision processes

Continual Learning of Control Primitives: Skill Discovery via Reset-Games

Rearrangement: A Challenge for Embodied AI

Making Sense of Reinforcement Learning and Probabilistic Inference

Emergence of Spatial Coordinates via Exploration

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation

Reinforcement Learning for Optimization of COVID-19 Mitigation policies

The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI

Double-Linear Thompson Sampling for Context-Attentive Bandits