AI Agent - arXivDaily 专题

2007.07356 2021-05-11 cs.LG cs.AI 62%

Efficient Empowerment Estimation for Unsupervised Stabilization

Ruihan Zhao, Kevin Lu, Pieter Abbeel, Stas Tiomkin

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

2105.03041 2021-05-10 cs.LG cs.AI 62%

Utilizing Skipped Frames in Action Repeats via Pseudo-Actions

Taisei Hashimoto, Yoshimasa Tsuruoka

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

Comments Deep Reinforcement Learning Workshop, NeurIPS 2020

2104.14917 2021-05-04 cs.LG cs.AI 62%

Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

Fuxian Li, Jie Feng, Huan Yan, Guangyin Jin, Depeng Jin, Yong Li

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

Comments 13 pages, journal

2103.13552 2021-05-03 cs.CL cs.AI 62%

Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents

Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht

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

Comments NAACL 2021. Project page: https://blindfolded.cs.princeton.edu

2104.13207 2021-04-28 cs.LG cs.AI 62%

SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents

Grgur Kovač, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer

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

Comments Accepted at NAACL ViGIL Workshop 2021

2104.11573 2021-04-26 cs.AI cs.CL 62%

Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AI

Michael Timothy Bennett, Yoshihiro Maruyama

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

Comments 7 pages, submitted to IEEE ICDL 2021

2006.13916 2021-04-16 cs.LG cs.AI cs.RO stat.ML 62%

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

Benjamin Eysenbach, Swapnil Asawa, Shreyas Chaudhari, Sergey Levine, Ruslan Salakhutdinov

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

Comments Published at ICLR 2021. Code (https://github.com/google-research/google-research/tree/master/darc) and blog post (https://blog.ml.cmu.edu/2020/07/31/maintaining-the-illusion-of-reality-transfer-in-rl-by-keeping-agents-in-the-darc)

2104.02661 2021-04-07 cs.LG cs.AI 62%

Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning

Haritha Jayasinghe, Tarindu Jayatilaka, Ravin Gunawardena, Uthayasanker Thayasivam

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

2012.00057 2021-03-30 cs.CV cs.AI cs.LG 62%

Move to See Better: Self-Improving Embodied Object Detection

Zhaoyuan Fang, Ayush Jain, Gabriel Sarch, Adam W. Harley, Katerina Fragkiadaki

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

Comments First three authors contributed equally. Project Page: https://ayushjain1144.github.io/SeeingByMoving/

2103.12142 2021-03-24 cs.LG cs.AI 62%

Combining Reward Information from Multiple Sources

Dmitrii Krasheninnikov, Rohin Shah, Herke van Hoof

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

2103.11542 2021-03-23 cs.LG cs.AI cs.IT math.IT 62%

Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks

Jian Wang, Chen Xu, Rong Li, Yiqun Ge, Jun Wang

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

Comments 14 figures, submitted to a journal for possible publication

2011.01758 2021-03-23 cs.LG cs.AI cs.RO stat.ML 62%

Representation Matters: Improving Perception and Exploration for Robotics

Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, Tejas Kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin Riedmiller

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

Comments Published at ICRA 2021

2001.05411 2021-03-23 cs.LG cs.AI stat.ML 62%

Lipschitz Lifelong Reinforcement Learning

Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman

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

Comments In proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), 21 pages, 11 figures

1911.05889 2021-03-23 cs.AI cs.CL 62%

Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

Haoyu Song, Wei-Nan Zhang, Jingwen Hu, Ting Liu

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

Comments AAAI20. Update code links

2002.04676 2021-03-22 cs.LG cs.AI stat.ML 62%

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Dmitrii Beloborodov, A. E. Ulanov, Jakob N. Foerster, Shimon Whiteson, A. I. Lvovsky

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

Comments Submitted to ICML 2020. 9 pages, 3 pdf figures. V2: fixed acknowledgements

Journal ref Machine Learning: Science and Technology, 2, 025009 (2021)

2010.02317 2021-03-19 cs.LG cs.AI 62%

Meta-Learning of Structured Task Distributions in Humans and Machines

Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen, Nathaniel D. Daw, Thomas L. Griffiths

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

Comments Accepted at ICLR 2021

2011.01488 2021-03-16 cs.LG cs.AI 62%

Multi-armed Bandits with Cost Subsidy

Deeksha Sinha, Karthik Abinav Sankararama, Abbas Kazerouni, Vashist Avadhanula

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

2103.05612 2021-03-10 cs.LG cs.AI 62%

Challenges for Reinforcement Learning in Healthcare

Elsa Riachi, Muhammad Mamdani, Michael Fralick, Frank Rudzicz

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

1905.05498 2021-03-09 cs.LG cs.AI stat.ML 62%

Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization

Binyamin Manela, Armin Biess

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

2103.03412 2021-03-08 cs.LG cs.AI 62%

Learning to Schedule DAG Tasks

Zhigang Hua, Feng Qi, Gan Liu, Shuang Yang

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

2012.06561 2021-03-03 cs.AI cs.CL cs.LO 62%

Comprehension and Knowledge

Pavel Naumov, Kevin Ros

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

Comments To appear in Proceedings 35th AAAI Conference on Artificial Intelligence (AAAI 21), February 2-9, 2021

2012.08383 2021-03-02 cs.CL cs.AI 62%

Keyword-Guided Neural Conversational Model

Peixiang Zhong, Yong Liu, Hao Wang, Chunyan Miao

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

Comments AAAI-2021

2006.12862 2021-02-23 cs.LG cs.AI 62%

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning

Roberta Raileanu, Max Goldstein, Denis Yarats, Ilya Kostrikov, Rob Fergus

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

2009.08507 2021-02-16 cs.AI cs.LG 62%

Reconstructing Actions To Explain Deep Reinforcement Learning

Xuan Chen, Zifan Wang, Yucai Fan, Bonan Jin, Piotr Mardziel, Carlee Joe-Wong, Anupam Datta

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

2010.02433 2021-02-12 cs.LG cs.AI 62%

Active Feature Acquisition with Generative Surrogate Models

Yang Li, Junier B. Oliva

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

2012.11538 2021-02-11 cs.LG cs.AI cs.RO 62%

Evaluating Agents without Rewards

Brendon Matusch, Jimmy Ba, Danijar Hafner

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

Comments 15 pages, 6 figures, 5 tables

2102.03921 2021-02-09 cs.LG cs.AI cs.CV 62%

Sparsely ensembled convolutional neural network classifiers via reinforcement learning

Roman Malashin

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

2101.09721 2021-02-09 cs.LG cs.AI cs.NE 62%

Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies

Fabio Ferreira, Thomas Nierhoff, Frank Hutter

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

Journal ref AAAI 2021 Meta-Learning Workshop

2102.02639 2021-02-05 cs.LG cs.AI cs.HC 62%

Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym

Matthew E. Taylor, Nicholas Nissen, Yuan Wang, Neda Navidi

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

2102.00424 2021-02-02 cs.CL cs.CV cs.LG 62%

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games

Alessandro Suglia, Yonatan Bisk, Ioannis Konstas, Antonio Vergari, Emanuele Bastianelli, Andrea Vanzo, Oliver Lemon

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

Comments Accepted paper for the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)

1. Agent评测 15801 篇

Efficient Empowerment Estimation for Unsupervised Stabilization

Utilizing Skipped Frames in Action Repeats via Pseudo-Actions

Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents

SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents

Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AI

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning

Move to See Better: Self-Improving Embodied Object Detection

Combining Reward Information from Multiple Sources

Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks

Representation Matters: Improving Perception and Exploration for Robotics

Lipschitz Lifelong Reinforcement Learning

Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Meta-Learning of Structured Task Distributions in Humans and Machines

Multi-armed Bandits with Cost Subsidy

Challenges for Reinforcement Learning in Healthcare

Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization

Learning to Schedule DAG Tasks

Comprehension and Knowledge

Keyword-Guided Neural Conversational Model

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning

Reconstructing Actions To Explain Deep Reinforcement Learning

Active Feature Acquisition with Generative Surrogate Models

Evaluating Agents without Rewards

Sparsely ensembled convolutional neural network classifiers via reinforcement learning

Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies

Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games