大模型推理能力 - arXivDaily 专题

2109.06807 2021-09-15 cs.CL cs.AI 62%

A Temporal Variational Model for Story Generation

David Wilmot, Frank Keller

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

Comments 9 pages, 19 with references and appendices, 6 figures, and 4 tables

2109.06689 2021-09-15 cs.MA cs.AI cs.LG 62%

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Yue Meng, Zengyi Qin, Chuchu Fan

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at IROS 2021

2109.06609 2021-09-15 cs.LG cs.AI 62%

DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning

Satheesh K. Perepu, Kaushik Dey

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2109.01178 2021-09-06 cs.AI cs.LG cs.MA 62%

Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts

Sage Bergerson

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

2106.04679 2021-08-23 cs.MA cs.AI cs.GT cs.LG cs.RO 62%

Self-Adaptive Swarm System (SASS)

Qin Yang

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments The Camera-ready version for IJCAI 2021 Doctoral Consortium

2108.06594 2021-08-21 cs.LG cs.AI 62%

Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs

Doseok Jang, Lucas Spangher, Manan Khattar, Utkarsha Agwan, Selvaprabuh Nadarajah, Costas Spanos

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: text overlap with arXiv:2104.14670

2108.07693 2021-08-18 cs.CY cs.AI cs.LG 62%

Demonstrating REACT: a Real-time Educational AI-powered Classroom Tool

Ajay Kulkarni, Olga Gkountouna

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Published in the 14th International Conference on Educational Data Mining (EDM21)

2108.06148 2021-08-16 cs.LG cs.AI 62%

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

Vasilii Davydov, Alexey Skrynnik, Konstantin Yakovlev, Aleksandr I. Panov

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments This is a preprint of the paper accepted to RCAI 2021. It contains 11 pages and 5 figures

2107.09767 2021-07-22 cs.AI cs.LG 62%

Explainable AI Enabled Inspection of Business Process Prediction Models

Chun Ouyang, Renuka Sindhgatta, Catarina Moreira

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 17 pages, 6 figures, 1 table

2107.01825 2021-07-06 cs.LG cs.AI 62%

Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation

Yao Yao, Li Xiao, Zhicheng An, Wanpeng Zhang, Dijun Luo

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 5 figures, accepted by IEEE International Conference on Robotics and Automation 2021 (IEEE ICRA 2021)

1909.07755 2021-06-30 cs.CL cs.LG 62%

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

Markus Eberts, Adrian Ulges

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Published at ECAI 2020; marginally revised version; because of new insights into evaluation metrics used in related work, we updated Table 1 and report both micro/macro averaged entity values for the ADE dataset

2106.08053 2021-06-16 cs.LG cs.AI 62%

On the Power of Multitask Representation Learning in Linear MDP

Rui Lu, Gao Huang, Simon S. Du

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2106.05842 2021-06-11 cs.LG cs.AI 62%

Causality in Neural Networks -- An Extended Abstract

Abbavaram Gowtham Reddy

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

2002.09127 2021-05-12 cs.CL cs.LG 62%

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.LG

Comments Bug fixed in Table 1

2105.03546 2021-05-11 cs.MA cs.AI cs.LG cs.RO 62%

Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies

Austin Anhkhoi Nguyen

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 50 pages, 40 figures

2008.07971 2021-05-11 cs.AI cs.LG cs.RO 62%

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

Florian Fuchs, Yunlong Song, Elia Kaufmann, Davide Scaramuzza, Peter Duerr

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted for Publication at the IEEE Robotics and Automation Letters (RA-L) 2021, and International Conference on Robots and Automation (ICRA) 2021

Journal ref IEEE Robotics and Automation Letters (RAL) 2021

2006.04599 2021-05-05 cs.CY cs.AI cs.LG 62%

Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms

Akshat Pandey, Aylin Caliskan

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 16 pages, 3 tables, 8 figures

Journal ref AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2021)

2105.00667 2021-05-04 cs.AI cs.CY cs.LG 62%

Explaining how your AI system is fair

Boris Ruf, Marcin Detyniecki

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the ACM CHI 2021 Workshop on Operationalizing Human-Centered Perspectives in Explainable AI

2104.10810 2021-04-23 cs.CL cs.AI cs.IR 62%

A Short Survey of Pre-trained Language Models for Conversational AI-A NewAge in NLP

Munazza Zaib, Quan Z. Sheng, Wei Emma Zhang

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

2006.03662 2021-04-21 cs.LG cs.AI cs.NE stat.ML 62%

Rapid Task-Solving in Novel Environments

Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2006.15720 2021-04-15 cs.CL cs.LG 62%

Progressive Generation of Long Text with Pretrained Language Models

Bowen Tan, Zichao Yang, Maruan AI-Shedivat, Eric P. Xing, Zhiting Hu

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.LG

Comments NAACL 2021, Code available at https://github.com/tanyuqian/progressive-generation

2101.10369 2021-04-02 eess.SP cs.AI cs.IT cs.LG math.IT stat.ML 62%

Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

Tze-Yang Tung, Szymon Kobus, Joan Roig Pujol, Deniz Gunduz

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2012.07436 2021-03-30 cs.LG cs.AI cs.IR 62%

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, Wancai Zhang

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 8 pages (main), 5 pages (appendix) and to be appeared in AAAI2021

2103.01933 2021-03-23 cs.AI cs.CV cs.LG stat.ML 62%

PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception

Aviv Netanyahu, Tianmin Shu, Boris Katz, Andrei Barbu, Joshua B. Tenenbaum

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments The first two authors contributed equally; AAAI 2021; 13 pages, 7 figures; Project page: https://www.tshu.io/PHASE

2103.09977 2021-03-19 cs.AI cs.CL 62%

Situated Language Learning via Interactive Narratives

Prithviraj Ammanabrolu, Mark O. Riedl

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Preprint. Under journal review

2101.04422 2021-03-16 cs.CE cs.AI cs.LG 62%

Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning

Quirin Göttl, Dominik G. Grimm, Jakob Burger

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2102.12432 2021-02-25 cs.RO cs.AI cs.LG cs.SY eess.SY 62%

Deep Reinforcement Learning for Safe Landing Site Selection with Concurrent Consideration of Divert Maneuvers

Keidai Iiyama, Kento Tomita, Bhavi A. Jagatia, Tatsuwaki Nakagawa, Koki Ho

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 25 pages, 14 figures, This paper is an updated version of Paper AAS 20-583 presented at the AAS/AIAA Astrodynamics Specialist Conference, Online

2102.01904 2021-02-04 cs.AI cs.LG cs.LO 62%

A Scalable Two Stage Approach to Computing Optimal Decision Sets

Alexey Ignatiev, Edward Lam, Peter J. Stuckey, Joao Marques-Silva

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

2101.11071 2021-01-28 cs.LG cs.AI stat.ML 62%

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 37 pages, initial submission, accepted at NeurIPS. arXiv admin note: substantial text overlap with arXiv:1904.10079

1904.10079 2021-01-20 cs.LG cs.AI stat.ML 62%

The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors

William H. Guss, Cayden Codel, Katja Hofmann, Brandon Houghton, Noboru Kuno, Stephanie Milani, Sharada Mohanty, Diego Perez Liebana, Ruslan Salakhutdinov, Nicholay Topin, Manuela Veloso, Phillip Wang

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments accepted at NeurIPS 2019, 28 pages

1. 规划推理 11120 篇

A Temporal Variational Model for Story Generation

Reactive and Safe Road User Simulations using Neural Barrier Certificates

DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning

Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts

Self-Adaptive Swarm System (SASS)

Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs

Demonstrating REACT: a Real-time Educational AI-powered Classroom Tool

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

Explainable AI Enabled Inspection of Business Process Prediction Models

Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

On the Power of Multitask Representation Learning in Linear MDP

Causality in Neural Networks -- An Extended Abstract

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms

Explaining how your AI system is fair

A Short Survey of Pre-trained Language Models for Conversational AI-A NewAge in NLP

Rapid Task-Solving in Novel Environments

Progressive Generation of Long Text with Pretrained Language Models

Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception

Situated Language Learning via Interactive Narratives

Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning

Deep Reinforcement Learning for Safe Landing Site Selection with Concurrent Consideration of Divert Maneuvers

A Scalable Two Stage Approach to Computing Optimal Decision Sets

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors