人工智能每日论文速递[08.23]
同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文
cs.AI 方向,今日共计12篇
[cs.AI]:
【1】 The double traveling salesman problem with partial last-in-first-out loading constraints
标题:部分后进先出装载约束的双旅行商问题
作者: Jonatas B. C. Chagas, Manuel Iori
链接:https://arxiv.org/abs/1908.08494
【2】 The many Shapley values for model explanation
标题:用于模型解释的许多Shapley值
作者: Mukund Sundararajan, Amir Najmi
链接:https://arxiv.org/abs/1908.08474
【3】 SCF2 -- an Argumentation Semantics for Rational Human Judgments on Argument Acceptability: Technical Report
标题:SCF2-论证可接受性理性人类判断的论证语义学:技术报告
作者: Marcos Cramer, Leendert van der Torre
链接:https://arxiv.org/abs/1908.08406
【4】 Report on the First Knowledge Graph Reasoning Challenge 2018 -- Toward the eXplainable AI System
标题:2018年首届知识图推理挑战赛报告-走向可解释的AI系统
作者: Takahiro Kawamura, Kouji Kozaki
链接:https://arxiv.org/abs/1908.08184
【5】 Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes
标题:马尔可夫决策过程中有效的策略外评估的双强化学习
作者: Nathan Kallus, Masatoshi Uehara
链接:https://arxiv.org/abs/1908.08526
【6】 Simulation Model of Two-Robot Cooperation in Common Operating Environment
标题:通用操作环境下双机器人协作的仿真模型
作者: V.Ya. Vilisov, A. I. Kulikov
链接:https://arxiv.org/abs/1908.08485
【7】 The compositionality of neural networks: integrating symbolism and connectionism
标题:神经网络的组合性:象征主义与联结主义的整合
作者: Dieuwke Hupkes, Elia Bruni
链接:https://arxiv.org/abs/1908.08351
【8】 A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
标题:一种多目标强化学习和策略自适应的广义算法
作者: Runzhe Yang, Karthik Narasimhan
链接:https://arxiv.org/abs/1908.08342
【9】 Measuring the Business Value of Recommender Systems
标题:衡量推荐系统的商业价值
作者: Dietmar Jannach, Michael Jugovac
链接:https://arxiv.org/abs/1908.08328
【10】 Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
标题:多通道BERT:一种面向开放领域问答的全局归一化BERT模型
作者: Zhiguo Wang, Bing Xiang
备注:To appear in EMNLP 2019
链接:https://arxiv.org/abs/1908.08167
【11】 Deep Reinforcement Learning for Foreign Exchange Trading
标题:外汇交易的深度强化学习
作者: Chun-Chieh Wang, Yun-Cheng Tsai
链接:https://arxiv.org/abs/1908.08036
【12】 Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding
标题:信道编码的强化学习:学习的比特翻转解码
作者: Fabrizio Carpi, Henry D. Pfister
链接:https://arxiv.org/abs/1906.04448
翻译:腾讯翻译君