人工智能每日论文速递[07.17]

同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)

cs.AI 方向,今日共计8篇

[cs.AI]:

【1】 Mediation Challenges and Socio-Technical Gaps for Explainable Deep Learning Applications
标题:可解释深度学习应用的中介挑战和社会技术差距
作者: Rafael Brandão, Carla Leitão
链接:https://arxiv.org/abs/1907.07178

【2】 On Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems
标题:多智能体系统中具有策略类型的最佳响应学习的收敛性和最优性
作者: Stefano V. Albrecht, Subramanian Ramamoorthy
备注:Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence (UAI), 2014. arXiv admin note: substantial text overlap with arXiv:1507.07688
链接:https://arxiv.org/abs/1907.06995

【3】 Logic Conditionals, Supervenience, and Selection Tasks
标题:逻辑条件、上级和选择任务
作者: Giovanni Sileno
链接:https://arxiv.org/abs/1907.06773

【4】 Adaptive Prior Selection for Repertoire-based Online Learning in Robotics
标题:机器人中基于谱库的在线学习的自适应先验选择
作者: Rituraj Kaushik, Jean-Baptiste Mouret
链接:https://arxiv.org/abs/1907.07029

【5】 Unforeseen Evidence
标题:不可预见的证据
作者: Evan Piermont
链接:https://arxiv.org/abs/1907.07019

【6】 Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving
标题:基于图像自主驾驶的模拟学习预训练改进强化学习
作者: Tianqi Wang, Dong Eui Chang
备注:5 pages, 2019 19th International Conference on Control, Automation and Systems (ICCAS 2019)
链接:https://arxiv.org/abs/1907.06838

【7】 Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
标题:在可解释机器学习中评价没有基本事实的解释
作者: Fan Yang, Xia Hu
链接:https://arxiv.org/abs/1907.06831

【8】 PPO Dash: Improving Generalization in Deep Reinforcement Learning
标题:PPO DASH:改进深度强化学习中的泛化
作者: Joe Booth
链接:https://arxiv.org/abs/1907.06704

翻译:腾讯翻译君

你可能感兴趣的:(人工智能每日论文速递[07.17])