cs.AI 方向,今日共计11篇
[cs.AI]:
【1】 Effective problem solving using SAT solvers
标题:使用SAT求解器有效解决问题
作者: Curtis Bright, Vijay Ganesh
链接:https://arxiv.org/abs/1906.06251
【2】 Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors
标题:通过联合编码网络结构和文本节点描述符嵌入生物医学本体
作者: Sotiris Kotitsas, Marianna Apidianaki
备注:Proceedings of the 18th Workshop on Biomedical Natural Language Processing (BioNLP 2019) of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy, 2019
链接:https://arxiv.org/abs/1906.05939
【3】 Provably Efficient $Q$-learning with Function Approximation via Distribution Shift Error Checking Oracle
标题:通过分布转移错误检查Oracle,具有函数逼近的高效$ Q $ -learning
作者: Simon S. Du, Hanrui Zhang
链接:https://arxiv.org/abs/1906.06321
【4】 Extensions of Generic DOL for Generic Ontology Design Patterns
标题:通用本体设计模式的通用DOL扩展
作者: Mihai Codescu, Till Mossakowski
链接:https://arxiv.org/abs/1906.06275
【5】 Epistemic Risk-Sensitive Reinforcement Learning
标题:认知风险敏感强化学习
作者: Hannes Eriksson, Christos Dimitrakakis
链接:https://arxiv.org/abs/1906.06273
【6】 Curriculum Learning for Cumulative Return Maximization
标题:累积回报最大化的课程学习
作者: Francesco Foglino, Matteo Leonetti
备注:Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19). arXiv admin note: text overlap with arXiv:1901.11478
链接:https://arxiv.org/abs/1906.06178
【7】 Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
标题:直接政策梯度:离散行动空间中政策的直接优化
作者: Guy Lorberbom, Daniel Tarlow
链接:https://arxiv.org/abs/1906.06062
【8】 Dynamic Term-Modal Logics for Epistemic Planning
标题:认知规划的动态术语 - 模态逻辑
作者: Andreas Achen, Rasmus K. Rendsvig
链接:https://arxiv.org/abs/1906.06047
【9】 Early Detection of Long Term Evaluation Criteria in Online Controlled Experiments
标题:早期检测在线控制实验的长期评估标准
作者: Yoni Schamroth, David Steinberg
链接:https://arxiv.org/abs/1906.05959
【10】 Sub-policy Adaptation for Hierarchical Reinforcement Learning
标题:分层强化学习的子策略适应
作者: Alexander C. Li, Pieter Abbeel
备注:Contributed talk at the Workshop on Multi-Task and Lifelong Reinforcement Learning at ICML 2019
链接:https://arxiv.org/abs/1906.05862
【11】 Meta-Learning via Learned Loss
标题:通过学习损失进行元学习
作者: Yevgen Chebotar, Gaurav Sukhatme
链接:https://arxiv.org/abs/1906.05374
翻译:谷歌翻译
领取专属 10元无门槛券
私享最新 技术干货