大模型推理能力 - arXivDaily 专题

2212.02435 2022-12-06 stat.ML cs.AI cs.LG 62%

Observational and Interventional Causal Learning for Regret-Minimizing Control

Christian Reiser

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

2202.07364 2022-12-01 cs.LG cs.AI cs.MA 62%

Zero-Shot Assistance in Sequential Decision Problems

Sebastiaan De Peuter, Samuel Kaski

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

Comments 9 pages, 8 appendix pages, 13 figures. Accepted for publication at AAAI-23

2209.10876 2022-11-29 cs.CL cs.LG 62%

An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification

Nikolaos Mylonas, Ioannis Mollas, Grigorios Tsoumakas

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

Comments 16 pages, 7 figures, 5 tables, Submitted to DAMI Journal (ECMLPKDD2023 Special Issue)

2211.07645 2022-11-16 cs.LG cs.AI stat.ML 62%

Evaluating Distribution System Reliability with Hyperstructures Graph Convolutional Nets

Yuzhou Chen, Tian Jiang, Miguel Heleno, Alexandre Moreira, Yulia R. Gel

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

Comments IEEE BigData 2022

2210.06464 2022-11-07 cs.LG cs.AI 62%

Predictive Querying for Autoregressive Neural Sequence Models

Alex Boyd, Sam Showalter, Stephan Mandt, Padhraic Smyth

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

Comments Oral Presentation at the Intl. Conference on Neural Information Processing Systems (NeurIPS 2022)

2210.02377 2022-10-26 cs.AI cs.LG 62%

Goal Recognition as a Deep Learning Task: the GRNet Approach

Mattia Chiari, Alfonso E. Gerevini, Luca Putelli, Francesco Percassi, Ivan Serina

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

2210.12308 2022-10-25 cs.LG cs.AI 62%

PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding

Niranjan Uma Naresh, Ziyan Jiang, Ankit, Sungjin Lee, Jie Hao, Xing Fan, Chenlei Guo

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

Comments EMNLP 2022

2206.08569 2022-10-19 cs.LG cs.AI cs.RO 62%

Bootstrapped Transformer for Offline Reinforcement Learning

Kerong Wang, Hanye Zhao, Xufang Luo, Kan Ren, Weinan Zhang, Dongsheng Li

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

Comments Accepted in NeurIPS 2022

2206.04199 2022-10-13 cs.AI cs.LG cs.NE 62%

Deep Surrogate Assisted Generation of Environments

Varun Bhatt, Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis

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

Comments 26 pages, 15 figures, supplemental website at https://dsagepaper.github.io/

2210.01258 2022-10-05 cs.CL cs.AI 62%

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

Ke Shen, Mayank Kejriwal

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

2204.13307 2022-09-27 cs.LG cs.AI cs.GT stat.ML 62%

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

Johannes Scheiermann, Wolfgang Konen

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

Comments 11 pages, 10 figures

2007.15619 2022-09-07 cs.CY cs.CL cs.LG 62%

AI-based Monitoring and Response System for Hospital Preparedness towards COVID-19 in Southeast Asia

Tushar Goswamy, Naishadh Parmar, Ayush Gupta, Raunak Shah, Vatsalya Tandon, Varun Goyal, Sanyog Gupta, Karishma Laud, Shivam Gupta, Sudhanshu Mishra, Ashutosh Modi

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

Comments 5 pages, 5 figures. Accepted to the ICML 2020 Workshop on Healthcare Systems, Population Health, and the Role of Health-Tech

2208.11535 2022-08-25 cs.LG cs.AI 62%

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers

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

2208.11404 2022-08-25 cs.LG cs.AI cs.CY cs.HC 62%

Augmented cross-selling through explainable AI -- a case from energy retailing

Felix Haag, Konstantin Hopf, Pedro Menelau Vasconcelos, Thorsten Staake

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

2208.06979 2022-08-16 cs.LG cs.AI cs.SI 62%

DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps

Jizhou Huang, Zhengjie Huang, Xiaomin Fang, Shikun Feng, Xuyi Chen, Jiaxiang Liu, Haitao Yuan, Haifeng Wang

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

Comments To appear at CIKM 2022

2104.00527 2022-07-22 cs.LG cs.AI math.OC physics.comp-ph physics.geo-ph 62%

Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow

Yusuf Nasir, Jincong He, Chaoshun Hu, Shusei Tanaka, Kainan Wang, XianHuan Wen

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

Comments Journal paper

Journal ref Front. Appl. Math. Stat. 7 (2021)

2207.06415 2022-07-15 cs.LG cs.AI q-bio.NC 62%

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

Pietro Mazzaglia, Tim Verbelen, Ozan Çatal, Bart Dhoedt

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

Journal ref Entropy 2022

2207.04361 2022-07-12 cs.RO cs.AI cs.LG 62%

State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections

Shivesh Khaitan, John M. Dolan

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

Comments 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 6 pages, 6 figures

2112.04153 2022-07-01 cs.LG cs.AI 62%

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

Angelos Filos, Eszter Vértes, Zita Marinho, Gregory Farquhar, Diana Borsa, Abram Friesen, Feryal Behbahani, Tom Schaul, André Barreto, Simon Osindero

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

Comments The first three authors contributed equally. Accepted at ICML 2022

2206.13754 2022-06-29 cs.MA cs.AI cs.LG 62%

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

Joe Eappen, Suresh Jagannathan

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

Comments ECML-PKDD 2022

2206.12493 2022-06-28 cs.AI cs.LG 62%

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments

Shivam Goel, Yash Shukla, Vasanth Sarathy, Matthias Scheutz, Jivko Sinapov

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

Comments Proceedings of the IEEE Conference on Development and Learning (ICDL 2022)

2206.10944 2022-06-23 cs.LG cs.AI cs.MA 62%

POGEMA: Partially Observable Grid Environment for Multiple Agents

Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr I. Panov

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

Comments 7 pages, 7 figures

2108.05030 2022-06-22 cs.RO cs.AI cs.LG cs.SY eess.SY 62%

DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks

Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu

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

Comments Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022

2206.02566 2022-06-07 cs.LG cs.AI cs.MA econ.TH 62%

Towards Group Learning: Distributed Weighting of Experts

Ben Abramowitz, Nicholas Mattei

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

2206.00059 2022-06-02 cs.CL cs.AI 62%

A Mixture-of-Expert Approach to RL-based Dialogue Management

Yinlam Chow, Aza Tulepbergenov, Ofir Nachum, MoonKyung Ryu, Mohammad Ghavamzadeh, Craig Boutilier

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

2205.13881 2022-05-30 cs.AI cs.LG cs.NE 62%

Automated Dynamic Algorithm Configuration

Steven Adriaensen, André Biedenkapp, Gresa Shala, Noor Awad, Theresa Eimer, Marius Lindauer, Frank Hutter

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

2205.10816 2022-05-24 cs.LG cs.AI 62%

Chain of Thought Imitation with Procedure Cloning

Mengjiao Yang, Dale Schuurmans, Pieter Abbeel, Ofir Nachum

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

2205.03692 2022-05-12 cs.CL cs.AI 62%

Towards a Progression-Aware Autonomous Dialogue Agent

Abraham Sanders, Tomek Strzalkowski, Mei Si, Albert Chang, Deepanshu Dey, Jonas Braasch, Dakuo Wang

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

Comments Accepted at NAACL 2022

2205.04139 2022-05-10 cs.LG cs.AI 62%

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

Thanh Tung Khuat, David Jacob Kedziora, Bogdan Gabrys

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

Comments Submitted to Foundations and Trends in Human-Computer Interaction

2109.07703 2022-05-02 cs.RO cs.AI cs.CV cs.LG 62%

ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI

Guanxiong Chen, Haoyu Yang, Ian M. Mitchell

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

Comments Camera-ready version submitted to Canadian Conference on Computer and Robot Vision (CRV) 2022

1. 规划推理 11120 篇

Observational and Interventional Causal Learning for Regret-Minimizing Control

Zero-Shot Assistance in Sequential Decision Problems

An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification

Evaluating Distribution System Reliability with Hyperstructures Graph Convolutional Nets

Predictive Querying for Autoregressive Neural Sequence Models

Goal Recognition as a Deep Learning Task: the GRNet Approach

PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding

Bootstrapped Transformer for Offline Reinforcement Learning

Deep Surrogate Assisted Generation of Environments

Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

AI-based Monitoring and Response System for Hospital Preparedness towards COVID-19 in Southeast Asia

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Augmented cross-selling through explainable AI -- a case from energy retailing

DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps

Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments

POGEMA: Partially Observable Grid Environment for Multiple Agents

DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks

Towards Group Learning: Distributed Weighting of Experts

A Mixture-of-Expert Approach to RL-based Dialogue Management

Automated Dynamic Algorithm Configuration

Chain of Thought Imitation with Procedure Cloning

Towards a Progression-Aware Autonomous Dialogue Agent

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI