AI Agent - arXivDaily 专题

2103.06443 2021-11-10 cs.RO cs.AI cs.CV cs.IR cs.LG 62%

Where is your place, Visual Place Recognition?

Sourav Garg, Tobias Fischer, Michael Milford

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

Comments Accepted to the International Joint Conference on Artificial Intelligence (IJCAI2021)

2110.14248 2021-10-29 cs.LG cs.AI 62%

Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jimmy Ba

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

Comments 33 pages

Journal ref NeurIPS2021

2109.08270 2021-10-26 cs.AI cs.CL 62%

Language Models as a Knowledge Source for Cognitive Agents

Robert E. Wray, III, James R. Kirk, John E. Laird

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

Comments 16 pages, 2 figures; accepted for 2021 Advances in Cognitive Systems Conference (revised based on reviews)

2103.12690 2021-10-22 cs.LG cs.AI stat.ML 62%

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap

Yuanhao Wang, Ruosong Wang, Sham M. Kakade

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

2102.02926 2021-10-22 cs.LG cs.AI 62%

Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

Jane X. Wang, Michael King, Nicolas Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, Francis Song, Gavin Buttimore, David P. Reichert, Neil Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick

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

Comments Published in Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 2021

2010.10216 2021-10-22 cs.CL cs.AI 62%

Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions

Biswesh Mohapatra, Gaurav Pandey, Danish Contractor, Sachindra Joshi

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

Comments Accepted in the Findings of EMNLP 2021

2110.09514 2021-10-19 cs.LG cs.AI cs.CV cs.RO stat.ML 62%

Discovering and Achieving Goals via World Models

Russell Mendonca, Oleh Rybkin, Kostas Daniilidis, Danijar Hafner, Deepak Pathak

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

Comments NeurIPS 2021. First two authors contributed equally. Website at https://orybkin.github.io/lexa/

2110.08307 2021-10-19 cs.LG cs.AI 62%

GrowSpace: Learning How to Shape Plants

Yasmeen Hitti, Ionelia Buzatu, Manuel Del Verme, Mark Lefsrud, Florian Golemo, Audrey Durand

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

2110.06912 2021-10-14 cs.RO cs.AI cs.LG 62%

OPEn: An Open-ended Physics Environment for Learning Without a Task

Chuang Gan, Abhishek Bhandwaldar, Antonio Torralba, Joshua B. Tenenbaum, Phillip Isola

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

Comments IROS 2021. Project page: http://open.csail.mit.edu/

2110.04749 2021-10-12 physics.pop-ph cs.AI cs.LG 62%

Modeling of Pan Evaporation Based on the Development of Machine Learning Methods

Mustafa Al-Mukhtar

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

2110.04647 2021-10-12 cs.LG cs.CL 62%

Learning to Follow Language Instructions with Compositional Policies

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Benjamin Rosman

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

Comments Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836)

2109.14516 2021-10-08 cs.LG cs.AI cs.NE cs.RO cs.SY eess.SY 62%

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

Anthony Courchesne, Andrea Censi, Liam Paull

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

Comments 8 pages, 6 figures Accepted & Presented at IROS2021 For associated code, see https://github.com/duckietown

2109.15147 2021-10-01 cs.AI cs.LG 62%

Reinforcement Learning with Information-Theoretic Actuation

Elliot Catt, Marcus Hutter, Joel Veness

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

2109.14703 2021-10-01 cs.LG cs.AI cs.DC cs.MA math.ST stat.TH 62%

Sequential Estimation under Multiple Resources: a Bandit Point of View

Alireza Masoumian, Shayan Kiyani, Mohammad Hossein Yassaee

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

Comments 19 pages, 1 figure, 1 algorithm

2109.13463 2021-09-29 cs.LG cs.AI 62%

Deep Reinforcement Learning with Adjustments

Hamed Khorasgani, Haiyan Wang, Chetan Gupta, Susumu Serita

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

2109.12112 2021-09-28 cs.AI cs.LG 62%

MCTS Based Agents for Multistage Single-Player Card Game

Konrad Godlewski, Bartosz Sawicki

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

Comments Published in 2020 IEEE 21st International Conference on Computational Problems of Electrical Engineering. arXiv admin note: text overlap with arXiv:2109.12001

2109.09371 2021-09-21 cs.AI cs.CL cs.NE stat.ML 62%

Learning Natural Language Generation from Scratch

Alice Martin Donati, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin

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

2012.11329 2021-09-21 cs.RO cs.AI cs.LG 62%

CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving

Błażej Osiński, Piotr Miłoś, Adam Jakubowski, Paweł Zięcina, Michał Martyniak, Christopher Galias, Antonia Breuer, Silviu Homoceanu, Henryk Michalewski

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

2012.11783 2021-09-17 eess.SP cs.AI cs.LG cs.MA cs.NI 62%

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

Wei Cui, Wei Yu

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

Comments 15 pages, 9 figures. To appear in IEEE Transactions on Communications

2109.06234 2021-09-15 cs.LG cs.AI 62%

Machine Learning for Online Algorithm Selection under Censored Feedback

Alexander Tornede, Viktor Bengs, Eyke Hüllermeier

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

2107.03190 2021-09-14 cs.AI cs.LG stat.ME 62%

Nested Counterfactual Identification from Arbitrary Surrogate Experiments

Juan D Correa, Sanghack Lee, Elias Bareinboim

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

2006.08767 2021-09-14 cs.LG cs.AI stat.ML 62%

Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning

Borja G. León, Murray Shanahan, Francesco Belardinelli

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

2109.04367 2021-09-10 cs.CL cs.CR cs.LG 62%

Multi-granularity Textual Adversarial Attack with Behavior Cloning

Yangyi Chen, Jin Su, Wei Wei

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

Comments Accepted by the main conference of EMNLP 2021

2104.09785 2021-09-10 eess.SY cs.AI cs.LG cs.SY math.OC 62%

Model-predictive control and reinforcement learning in multi-energy system case studies

Glenn Ceusters, Román Cantú Rodríguez, Alberte Bouso García, Rüdiger Franke, Geert Deconinck, Lieve Helsen, Ann Nowé, Maarten Messagie, Luis Ramirez Camargo

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

Comments 43 pages, 29 figures

1910.01723 2021-09-07 cs.LG cs.AI stat.ML 62%

Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning

Kolby Nottingham, Anand Balakrishnan, Jyotirmoy Deshmukh, David Wingate

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

2108.09402 2021-08-24 cs.LG cs.AI cs.SI 62%

A Multi-Task Learning Framework for COVID-19 Monitoring and Prediction of PPE Demand in Community Health Centres

Bonaventure Chidube Molokwu, Shaon Bhatta Shuvo, Ziad Kobti, Anne Snowdon

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

Comments 6-page article/manuscript

2012.02671 2021-08-23 cs.AI cs.GT cs.LG 62%

Learning in two-player games between transparent opponents

Adrian Hutter

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

Comments 30 pages, 14 figures; v2: includes changes based on peer feedback

2108.05701 2021-08-13 cs.LG cs.AI cs.CV cs.GT 62%

An Approach to Partial Observability in Games: Learning to Both Act and Observe

Elizabeth Gilmour, Noah Plotkin, Leslie Smith

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

Comments 5 pages, 5 figures, to be published in proceedings of IEEE Conference on Games 2021

2108.01442 2021-08-04 cs.IR cs.AI cs.LG 62%

Sequence Adaptation via Reinforcement Learning in Recommender Systems

Stefanos Antaris, Dimitrios Rafailidis

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

2011.06775 2021-08-02 cs.RO cs.AI cs.LG cs.SY eess.SY 62%

DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks

Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu

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

Comments IROS 2021, 6 pages

1. Agent评测 15801 篇

Where is your place, Visual Place Recognition?

Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Language Models as a Knowledge Source for Cognitive Agents

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap

Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions

Discovering and Achieving Goals via World Models

GrowSpace: Learning How to Shape Plants

OPEn: An Open-ended Physics Environment for Learning Without a Task

Modeling of Pan Evaporation Based on the Development of Machine Learning Methods

Learning to Follow Language Instructions with Compositional Policies

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

Reinforcement Learning with Information-Theoretic Actuation

Sequential Estimation under Multiple Resources: a Bandit Point of View

Deep Reinforcement Learning with Adjustments

MCTS Based Agents for Multistage Single-Player Card Game

Learning Natural Language Generation from Scratch

CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

Machine Learning for Online Algorithm Selection under Censored Feedback

Nested Counterfactual Identification from Arbitrary Surrogate Experiments

Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning

Multi-granularity Textual Adversarial Attack with Behavior Cloning

Model-predictive control and reinforcement learning in multi-energy system case studies

Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning

A Multi-Task Learning Framework for COVID-19 Monitoring and Prediction of PPE Demand in Community Health Centres

Learning in two-player games between transparent opponents

An Approach to Partial Observability in Games: Learning to Both Act and Observe

Sequence Adaptation via Reinforcement Learning in Recommender Systems

DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks