AI Agent - arXivDaily 专题

2110.11222 2022-02-08 cs.LG cs.AI 62%

Is High Variance Unavoidable in RL? A Case Study in Continuous Control

Johan Bjorck, Carla P. Gomes, Kilian Q. Weinberger

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ICLR2022

2106.13008 2022-01-10 cs.LG cs.AI 62%

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long

专题命中软件智能体：planning(abstract)；分类 cs.AI、cs.LG

2110.14615 2021-12-15 cs.AI cs.CY cs.LG 62%

Play to Grade: Testing Coding Games as Classifying Markov Decision Process

Allen Nie, Emma Brunskill, Chris Piech

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2021, 16 pages, 7 figures

2112.01195 2021-12-03 cs.AI cs.LG 62%

Maximum Entropy Model-based Reinforcement Learning

Oleg Svidchenko, Aleksei Shpilman

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS'2021 Deep Reinforcement Learning Workshop

2008.01976 2021-11-12 cs.LG cs.AI cs.CR stat.ML 62%

Robust Deep Reinforcement Learning through Adversarial Loss

Tuomas Oikarinen, Wang Zhang, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2109.06554 2021-09-17 cs.CL cs.AI cs.LO 62%

Talking Space: inference from spatial linguistic meanings

Vincent Wang-Mascianica, Bob Coecke

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.CL

Comments 33 pages, many pictures

2105.01060 2021-09-01 cs.CV cs.AI cs.LG cs.RO 62%

Curious Representation Learning for Embodied Intelligence

Yilun Du, Chuang Gan, Phillip Isola

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments To apear at ICCV 2021. Code is available at https://yilundu.github.io/crl

2107.06661 2021-07-15 cs.AI cs.LG cs.RO 62%

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Ingmar Schubert, Ozgur S. Oguz, Marc Toussaint

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Published as a conference paper at ICLR 2021

Journal ref ICLR 2021 - 9th International Conference on Learning Representations

2107.02195 2021-07-07 cs.LG cs.AI 62%

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems

Shashank Hegde, Anssi Kanervisto, Aleksei Petrenko

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in IEEE Conference on Games 2021. Video demonstrations and experiment can be found at https://sites.google.com/view/sound-rl

2106.06135 2021-06-14 cs.AI cs.LG 62%

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu

专题命中软件智能体：AI agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted by ICML 2021

2106.05506 2021-06-11 cs.AI cs.LG 62%

Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program

Jeff Druce, James Niehaus, Vanessa Moody, David Jensen, Michael L. Littman

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2004.04778 2021-05-28 cs.AI cs.LG cs.MA 62%

Quantifying the Impact of Non-Stationarity in Reinforcement Learning-Based Traffic Signal Control

Lucas N. Alegre, Ana L. C. Bazzan, Bruno C. da Silva

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages

Journal ref PeerJ Computer Science 2021

2103.03912 2021-03-09 cs.AI cs.LG 62%

Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders

Albert Dulian, John C. Murray

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2010.05767 2021-03-03 cs.LG cs.AI stat.ML 62%

Smaller World Models for Reinforcement Learning

Jan Robine, Tobias Uelwer, Stefan Harmeling

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

2010.04003 2021-02-26 cs.LG cs.AI stat.ML 62%

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

Thang Doan, Mehdi Bennani, Bogdan Mazoure, Guillaume Rabusseau, Pierre Alquier

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to AISTATS 2021. Keywords: continual learning, catastrophic forgetting, NTK regime, orthgonal gradient descent

Journal ref Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)

2102.05710 2021-02-12 cs.LG cs.AI 62%

Derivative-Free Reinforcement Learning: A Review

Hong Qian, Yang Yu

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments This article has been accepted by Frontiers of Computer Science in 2020

1810.07207 2021-01-12 quant-ph cs.AI cs.LG 62%

Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation

Ryan Sweke, Markus S. Kesselring, Evert P. L. van Nieuwenburg, Jens Eisert

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures, associated code repository available at https://github.com/R-Sweke/DeepQ-Decoding

Journal ref Mach. Learn. Sci. Technol. 2, 025005 (2021)

2012.08148 2020-12-16 cs.CL cs.AI 62%

A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer

Matteo A. Senese, Alberto Benincasa, Barbara Caputo, Giuseppe Rizzo

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.CL

2010.15597 2020-10-30 cs.LG cs.AI 62%

Enhancing reinforcement learning by a finite reward response filter with a case study in intelligent structural control

Hamid Radmard Rahmani, Carsten Koenke, Marco A. Wiering

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 16 pages, 16 figures

2010.11944 2020-10-23 cs.LG cs.AI cs.RO 62%

Accelerating Reinforcement Learning with Learned Skill Priors

Karl Pertsch, Youngwoon Lee, Joseph J. Lim

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 4th Conference on Robot Learning (CoRL), 2020

2009.12683 2020-09-29 cs.LG cs.CL stat.ML 62%

Reinforcement Learning-based N-ary Cross-Sentence Relation Extraction

Chenhan Yuan, Ryan Rossi, Andrew Katz, Hoda Eldardiry

专题命中软件智能体：agent(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, 3 figures, submitted to AAAI

2008.09680 2020-08-31 cs.AI cs.LG cs.PL 62%

Transforming Probabilistic Programs for Model Checking

Ryan Bernstein, Matthijs Vákár, Jeannette Wing

专题命中软件智能体：workflow(abstract)；分类 cs.AI、cs.LG

Comments To be published in Proceedings of the 2020 ACM-IMS Foundations of Data Science Conference

2008.07434 2020-08-18 cs.LG cs.AI 62%

Integrating Deep Reinforcement Learning Networks with Health System Simulations

Michael Allen, Thomas Monks

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 6 pages, 1 figure

1910.12134 2020-04-24 cs.LG cs.AI stat.ML 62%

Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS

Shengyi Huang, Santiago Ontañón

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented in the AIIDE 2019 Workshop on Artificial Intelligence for Strategy Games

1812.08451 2020-04-10 quant-ph cs.AI cs.LG 62%

Optimizing Quantum Error Correction Codes with Reinforcement Learning

Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Briegel, Nicolai Friis

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments 21 pages, 13 figures, 1 table, updated reference list, accepted for publication in Quantum

Journal ref Quantum 3, 215 (2019)

2003.06212 2020-03-16 cs.AI cs.LG cs.MA cs.NE 62%

Accelerating and Improving AlphaZero Using Population Based Training

Ti-Rong Wu, Ting-Han Wei, I-Chen Wu

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments accepted by AAAI2020 as oral presentation. In this version, supplementary materials are added

1910.10537 2020-03-09 cs.LG cs.AI 62%

Robust Visual Domain Randomization for Reinforcement Learning

Reda Bahi Slaoui, William R. Clements, Jakob N. Foerster, Sébastien Toth

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the BeTR-RL Workshop at ICLR 2020

2002.05432 2020-02-14 cs.SE cs.LG 62%

The PHOTON Wizard -- Towards Educational Machine Learning Code Generators

Ramona Leenings, Nils Ralf Winter, Kelvin Sarink, Jan Ernsting, Xiaoyi Jiang, Udo Dannlowski, Tim Hahn

专题命中软件智能体：workflow(abstract)；分类 cs.LG、cs.SE

1912.07670 2019-12-18 cs.RO cs.AI cs.LG 62%

To Follow or not to Follow: Selective Imitation Learning from Observations

Youngwoon Lee, Edward S. Hu, Zhengyu Yang, Joseph J. Lim

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at the Conference on Robot Learning (CoRL) 2019

1909.04368 2019-09-11 cs.AI cs.SE 62%

Automatic difficulty management and testing in games using a framework based on behavior trees and genetic algorithms

Ciprian Paduraru, Miruna Paduraru

专题命中软件智能体：agent(abstract)；分类 cs.AI、cs.SE

Comments Accepted for publication in the IEEE Proceedings of The 24 International Conference on Engineering of Complex Computer Systems (ICECCS 2019)

1. 软件智能体 3217 篇

Is High Variance Unavoidable in RL? A Case Study in Continuous Control

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Play to Grade: Testing Coding Games as Classifying Markov Decision Process

Maximum Entropy Model-based Reinforcement Learning

Robust Deep Reinforcement Learning through Adversarial Loss

Talking Space: inference from spatial linguistic meanings

Curious Representation Learning for Embodied Intelligence

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program

Quantifying the Impact of Non-Stationarity in Reinforcement Learning-Based Traffic Signal Control

Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders

Smaller World Models for Reinforcement Learning

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

Derivative-Free Reinforcement Learning: A Review

Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation

A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer

Enhancing reinforcement learning by a finite reward response filter with a case study in intelligent structural control

Accelerating Reinforcement Learning with Learned Skill Priors

Reinforcement Learning-based N-ary Cross-Sentence Relation Extraction

Transforming Probabilistic Programs for Model Checking

Integrating Deep Reinforcement Learning Networks with Health System Simulations

Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS

Optimizing Quantum Error Correction Codes with Reinforcement Learning

Accelerating and Improving AlphaZero Using Population Based Training

Robust Visual Domain Randomization for Reinforcement Learning

The PHOTON Wizard -- Towards Educational Machine Learning Code Generators

To Follow or not to Follow: Selective Imitation Learning from Observations

Automatic difficulty management and testing in games using a framework based on behavior trees and genetic algorithms