AAAI-2020 || 52篇深度强化学习accept论文汇总

深度强化学习实验室报道

来源：AAAI-2020

作者：DeepRL

AAAI 2020 共收到的有效论文投稿超过 8800 篇，其中 7737 篇论文进入评审环节，最终收录数量为 1591 篇，收录率为 20.6%，而被接受论文列表中强化学习有52+篇，录取比约为3%，其中接收论文中就单位而言：Google Brain, DeepMind, Tsinghua University,UCL,Tencent AI Lab,Peking University, IBM, FaceBook等被录取一大片，就作者而言，不但有强化学习老爷子Sutton的文章(第48篇)，也有后起之秀等。论文涉及了环境、理论算法、应用以及多智能体等各个方向。以下是详细列表：

[1]. Google Research Football: A Novel Reinforcement Learning Environment

Karol Kurach (Google Brain)*; Anton Raichuk (Google); Piotr Stańczyk (Google Brain); Michał Zając (Google Brain); Olivier Bachem (Google Brain); Lasse Espeholt (DeepMind); Carlos Riquelme (Google Brain); Damien Vincent (Google Brain); Marcin Michalski (Google); Olivier Bousquet (Google); Sylvain Gelly (Google Brain)

[2]. Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance

Xiaojian Ma (University of California, Los Angeles)*; Mingxuan Jing (Tsinghua University); Wenbing Huang (Tsinghua University); Chao Yang (Tsinghua University); Fuchun Sun (Tsinghua); Huaping Liu (Tsinghua University); Bin Fang (Tsinghua University)

[3]. Proximal Distilled Evolutionary Reinforcement Learning

Cristian Bodnar (University of Cambridge)*; Ben Day (University of Cambridge); Pietro Lió (University of Cambridge)

[4]. Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video

Jie Wu (Sun Yat-sen University)*; Guanbin Li (Sun Yat-­sen University); si liu (Beihang University); Liang Lin (DarkMatter AI)

[5]. RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

Nan Jiang (Tsinghua University)*; Sheng Jin (Tsinghua University); Zhiyao Duan (Unversity of Rochester); Changshui Zhang (Tsinghua University)

[6]. Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

Deheng Ye (Tencent)*; Zhao Liu (Tencent); Mingfei Sun (Tencent); Bei Shi (Tencent AI Lab); Peilin Zhao (Tencent AI Lab); Hao Wu (Tencent); Hongsheng Yu (Tencent); Shaojie Yang (Tencent); Xipeng Wu (Tencent); Qingwei Guo (Tsinghua University); Qiaobo Chen (Tencent); Yinyuting Yin (Tencent); Hao Zhang (Tencent); Tengfei Shi (Tencent); Liang Wang (Tencent); Qiang Fu (Tencent AI Lab); Wei Yang (Tencent AI Lab); Lanxiao Huang (Tencent)

[7]. Partner Selection for the Emergence of Cooperation in Multi‐Agent Systems using Reinforcement Learning

Nicolas Anastassacos (The Alan Turing Institute)*; Steve Hailes (University College London); Mirco Musolesi (UCL)

[8]. Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents

Felipe Leno da Silva (University of Sao Paulo)*; Pablo Hernandez-Leal (Borealis AI); Bilal Kartal (Borealis AI); Matthew Taylor (Borealis AI)

[9]. MetaLight: Value-based Meta-reinforcement Learning for Traffic Signal Control

Xinshi Zang (Shanghai Jiao Tong University)*; Huaxiu Yao (Pennsylvania State University); Guanjie Zheng (Pennsylvania State University); Nan Xu (University of Southern California); Kai Xu (Shanghai Tianrang Intelligent Technology Co., Ltd); Zhenhui (Jessie) Li (Penn State University)

[10].Adaptive Quantitative Trading: an Imitative Deep Reinforcement Learning Approach

Yang Liu (University of Science and Technology of China)*; Qi Liu (" University of Science and Technology of China, China"); Hongke Zhao (Tianjin University); Zhen Pan (University of Science and Technology of China); Chuanren Liu (The University of Tennessee Knoxville)

[11]. Neighborhood Cognition Consistent Multi‐Agent Reinforcement Learning

Hangyu Mao (Peking University)*; Wulong Liu (Huawei Noah's Ark Lab); Jianye Hao (Tianjin University); Jun Luo (Huawei Technologies Canada Co. Ltd.); Dong Li ( Huawei Noah's Ark Lab); Zhengchao Zhang (Peking University); Jun Wang (UCL); Zhen Xiao (Peking University)

[12]. SMIX( ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning

Chao Wen (Nanjing University of Aeronautics and Astronautics)*; Xinghu Yao (Nanjing University of Aeronautics and Astronautics); Yuhui Wang (Nanjing University of Aeronautics and Astronautics, China); Xiaoyang Tan (Nanjing University of Aeronautics and Astronautics, China)

[13]. Unpaired Image Enhancement Featuring Reinforcement-­Learning-Controlled Image Editing Software

Satoshi Kosugi (The University of Tokyo)*; Toshihiko Yamasaki (The University of Tokyo)

[14]. Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

Jun Wang (University of Science and Technology of China)*; Hefu Zhang (University of Science and Technology of China); Qi Liu (" University of Science and Technology of China, China"); Zhen Pan (University of Science and Technology of China); Hanqing Tao (University of Science and Technology of China (USTC))

[15]. Model and Reinforcement Learning for Markov Games with Risk Preferences

Wenjie Huang (Shenzhen Research Institute of Big Data)*; Hai Pham Viet (Department of Computer Science, School of Computing, National University of Singapore); William Benjamin Haskell (Supply Chain and Operations Management Area, Krannert School of Management, Purdue University)

[16]. Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning

Liang Tong (Washington University in Saint Louis)*; Aron Laszka (University of Houston); Chao Yan (Vanderbilt UNIVERSITY); Ning Zhang (Washington University in St. Louis); Yevgeniy Vorobeychik (Washington University in St. Louis)

[17]. Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large‐Scale Traffic Signal Control

Chacha Chen (Pennsylvania State University)*; Hua Wei (Pennsylvania State University); Nan Xu (University of Southern California); Guanjie Zheng (Pennsylvania State University); Ming Yang (Shanghai Tianrang Intelligent Technology Co., Ltd); Yuanhao Xiong (Zhejiang University); Kai Xu (Shanghai Tianrang Intelligent Technology Co., Ltd); Zhenhui (Jessie) Li (Penn State University)

[18]. Deep Reinforcement Learning for Active Human Pose Estimation

Erik Gärtner (Lund University)*; Aleksis Pirinen (Lund University); Cristian Sminchisescu (Lund University)

[19]. Be Relevant, Non‐redundant, Timely: Deep Reinforcement Learning for Real‐time Event Summarization

Min Yang ( Chinese Academy of Sciences)*; Chengming Li (Chinese Academy of Sciences); Fei Sun (Alibaba Group); Zhou Zhao (Zhejiang University); Ying Shen (Peking University Shenzhen Graduate School); Chenglin Wu (fuzhi.ai)

[20]. A Tale of Two‐Timescale Reinforcement Learning with the Tightest Finite‐Time Bound

Gal Dalal (Technion)*; Balazs Szorenyi (Yahoo Research); Gugan Thoppe (Duke University)

[21]. Reinforcement Learning with Perturbed Rewards

Jingkang Wang (University of Toronto); Yang Liu (UCSC); Bo Li (University of Illinois at Urbana–Champaign)*

[22]. Exploratory Combinatorial Optimization with Reinforcement Learning

Thomas Barrett (University of Oxford)*; William Clements (Unchartech); Jakob Foerster (Facebook AI Research); Alexander Lvovsky (Oxford University)

[23]. Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

Vishal Jain (Mila, McGill University)*; Liam Fedus (Google); Hugo Larochelle (Google); Doina Precup (McGill University); Marc G. Bellemare (Google Brain)

[24]. Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents

Xian Yeow Lee (Iowa State University)*; Sambit Ghadai (Iowa State University); Kai Liang Tan (Iowa State University); Chinmay Hegde (New York University); Soumik Sarkar (Iowa State University)

[25]. Modelling Sentence Pairs via Reinforcement Learning: An Actor‐Critic Approach to Learn the Irrelevant Words

MAHTAB AHMED (The University of Western Ontario)*; Robert Mercer (The University of Western Ontario)

[26]. Transfer Reinforcement Learning using Output-­Gated Working Memory

Arthur Williams (Middle Tennessee State University)*; Joshua Phillips (Middle Tennessee State University)

[27]. Reinforcement-­Learning based Portfolio Management with Augmented Asset Movement Prediction States

Yunan Ye (Zhejiang University)*; Hengzhi Pei (Fudan University); Boxin Wang (University of Illinois at Urbana-­ Champaign); Pin-­Yu Chen (IBM Research); Yada Zhu (IBM Research); Jun Xiao (Zhejiang University); Bo Li (University of Illinois at Urbana–Champaign)

[28]. Deep Reinforcement Learning for General Game Playing

Adrian Goldwaser (University of New South Wales)*; Michael Thielscher (University of New South Wales)

[29]. Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Jianwen Sun (Nanyang Technological University)*; Tianwei Zhang ( Nanyang Technological University); Xiaofei Xie (Nanyang Technological University); Lei Ma (Kyushu University); Yan Zheng (Tianjin University); Kangjie Chen (Tianjin University); Yang Liu (Nanyang Technology University, Singapore)

[30]. LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-­Based Games

Leonard Adolphs (ETHZ)*; Thomas Hofmann (ETH Zurich)

[31]. Induction of Subgoal Automata for Reinforcement Learning

Daniel Furelos-­Blanco (Imperial College London)*; Mark Law (Imperial College London); Alessandra Russo (Imperial College London); Krysia Broda (Imperial College London); Anders Jonsson (UPF)

[32]. MRI Reconstruction with Interpretable Pixel-­Wise Operations Using Reinforcement Learning

wentian li (Tsinghua University)*; XIDONG FENG (department of Automation,Tsinghua University); Haotian An (Tsinghua University); Xiang Yao Ng (Tsinghua University); Yu-­Jin Zhang (Tsinghua University)

[33]. Explainable Reinforcement Learning Through a Causal Lens

Prashan Madumal (University of Melbourne)*; Tim Miller (University of Melbourne); Liz Sonenberg (University of Melbourne); Frank Vetere (University of Melbourne)

[34]. Reinforcement Learning based Metapath Discovery in Large-­scale Heterogeneous Information Networks

Guojia Wan (Wuhan University); Bo Du (School of Compuer Science, Wuhan University)*; Shirui Pan (Monash University); Reza Haffari (Monash University, Australia)

[35]. Reinforcement Learning When All Actions are Not Always Available

Yash Chandak (University of Massachusetts Amherst)*; Georgios Theocharous ("Adobe Research, USA"); Blossom Metevier (University of Massachusetts, Amherst); Philip Thomas (University of Massachusetts Amherst)

[36]. Reinforcement Mechanism Design: With Applications to Dynamic Pricing in Sponsored Search Auctions

Weiran Shen (Carnegie Mellon University)*; Binghui Peng (Columbia University); Hanpeng Liu (Tsinghua University); Michael Zhang (Chinese University of Hong Kong); Ruohan Qian (Baidu Inc.); Yan Hong (Baidu Inc.); Zhi Guo (Baidu Inc.); Zongyao Ding (Baidu Inc.); Pengjun Lu (Baidu Inc.); Pingzhong Tang (Tsinghua University)

[37]. Metareasoning in Modular Software Systems: On-­the-­Fly Configuration Using Reinforcement Learning

Rich Contextual Representations Aditya Modi (Univ. of Michigan Ann Arbor)*; Debadeepta Dey (Microsoft); Alekh Agarwal (Microsoft); Adith Swaminathan (Microsoft Research); Besmira Nushi (Microsoft Research); Sean Andrist (Microsoft Research); Eric Horvitz (MSR)

[38]. Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model

Ya Xiao (Tongji University)*; Chengxiang Tan (Tongji University); Zhijie Fan (The Third Research Institute of the Ministry of Public Security); Qian Xu (Tongji University); Wenye Zhu (Tongji University)

[39]. Reinforcement Learning of Risk-­Constrained Policies in Markov Decision Processes

Tomas Brazdil (Masaryk University); Krishnendu Chatterjee (IST Austria); Petr Novotný (Masaryk University)*; Jiří Vahala (Masaryk University)

[40]. Deep Model-­Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

Qi Zhou (University of Science and Technology of China); Houqiang Li (University of Science and Technology of China); Jie Wang (University of Science and Technology of China)*

[41]. Reinforcement Learning with Non-­Markovian Rewards

Maor Gaon (Ben-­Gurion University); Ronen Brafman (BGU)*

[42]. Modular Robot Design Synthesis with Deep Reinforcement Learning

Julian Whitman (Carnegie Mellon University)*; Raunaq Bhirangi (Carnegie Mellon University); Matthew Travers (CMU); Howie Choset (Carnegie Melon University)

[42]. BAR -­A Reinforcement Learning Agent for Bounding-­Box Automated Refinement

Morgane Ayle (American University of Beirut -­ AUB)*; Jimmy Tekli (BMW Group / Université de Franche-­Comté -­ UFC); Julia Zini (American University of Beirut -­ AUB); Boulos El Asmar (BMW Group / Karlsruher Institut für Technologie -­ KIT); Mariette Awad (American University of Beirut-­ AUB)

[44]. Hierarchical Reinforcement Learning for Open-­Domain Dialog

Abdelrhman Saleh (Harvard University)*; Natasha Jaques (MIT); Asma Ghandeharioun (MIT); Judy Hanwen Shen(MIT); Rosalind Picard (MIT Media Lab)

[45]. Copy or Rewrite: Hybrid Summarization with Hierarchical Reinforcement Learning

Liqiang Xiao (Artificial Intelligence Institute, SJTU)*; Lu Wang (Khoury College of Computer Science, Northeastern University); Hao He (Shanghai Jiao Tong University); Yaohui Jin (Artificial Intelligence Institute, SJTU)

[46]. Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning

Xiang Ni (IBM Research); Jing Li (NJIT); Wang Zhou (IBM Research); Mo Yu (IBM T. J. Watson)*; Kun-­Lung Wu (IBM Research)

[47]. Actor Critic Deep Reinforcement Learning for Neural Malware Control

Yu Wang (Microsoft)*; Jack Stokes (Microsoft Research); Mady Marinescu (Microsoft Corporation)

[48]. Fixed-­Horizon Temporal Difference Methods for Stable Reinforcement Learning

Kristopher De Asis (University of Alberta)*; Alan Chan (University of Alberta); Silviu Pitis (University of Toronto); Richard Sutton (University of Alberta) ; Daniel Graves (Huawei)

[49]. Sequence Generation with Optimal-­Transport-­Enhanced Reinforcement Learning

Liqun Chen (Duke University)*; Ke Bai (Duke University); Chenyang Tao (Duke University); Yizhe Zhang (Microsoft Research); Guoyin Wang (Duke University); Wenlin Wang (Duke Univeristy); Ricardo Henao (Duke University); Lawrence Carin Duke (CS)

[50]. Scaling All-­Goals Updates in Reinforcement Learning Using Convolutional Neural Networks

Fabio Pardo (Imperial College London)*; Vitaly Levdik (Imperial College London); Petar Kormushev (Imperial College London)

[51]. Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning

Tian Tan (Stanford University)*; Zhihan Xiong (Stanford University); Vikranth Dwaracherla (Stanford University)

[52]. Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning

Sanket Shah (Singpore Management University)*; Arunesh Sinha (Singapore Management University); Pradeep Varakantham (Singapore Management University); Andrew Perrault (Harvard University); Milind Tambe (Harvard University)

可关注公众，添加微信助手讨论交流论文

关于论文的详细解读请查看Github：

https://github.com/NeuronDance/DeepRL/tree/master/DRL-ConferencePaper/AAAI/2020

# 往期论文精彩回顾#

第39篇：DQN系列(2): Double DQN 算法原理与实现

第38篇：DQN系列(1): Double Q-learning

第37篇：从Paper到Coding, 一览DRL挑战34类游戏

第36篇：复现"深度强化学习"论文的经验之谈

第35篇：α-Rank算法之DeepMind及Huawei的改进

第34篇：DeepMind-102页深度强化学习PPT(2019）

第33篇：全网首发|| 最全深度强化学习资料(永久更新)

第32篇：腾讯AI Lab强化学习招聘(正式/实习)

第31篇：强化学习，路在何方？

第30篇：强化学习的三种范例

第29篇：框架ES-MAML：进化策略的元学习方法

第28篇：138页“策略优化”PPT--Pieter Abbeel

第27篇：迁移学习在强化学习中的应用及最新进展

第26篇：深入理解Hindsight Experience Replay

第25篇：10项【深度强化学习】赛事汇总

第24篇：DRL实验中到底需要多少个随机种子？

第23篇：142页"ICML会议"强化学习笔记

第22篇：通过深度强化学习实现通用量子控制

第21篇：《深度强化学习》面试题汇总

第20篇：《深度强化学习》招聘汇总(13家企业）

第19篇：解决反馈稀疏问题之HER原理与代码实现

第18篇："DeepRacer" —顶级深度强化学习挑战赛

第17篇：AI Paper | 几个实用工具推荐

第16篇：AI领域：如何做优秀研究并写高水平论文？

第15篇： DeepMind开源三大新框架！

第14篇： 61篇NIPS2019深度强化学习论文及部分解读

第13篇： OpenSpiel(28种DRL环境+24种DRL算法)

第12篇： 模块化和快速原型设计的Huskarl DRL框架

第11篇： DRL在Unity自行车环境中配置与实践

第10篇： 解读72篇DeepMind深度强化学习论文

第9篇： 《AutoML》：一份自动化调参的指导

第8篇： ReinforceJS库（动态展示DP、TD、DQN）

第7篇： 10年NIPS顶会DRL论文(100多篇)汇总

第6篇： ICML2019-深度强化学习文章汇总

第5篇： 深度强化学习在阿里巴巴的技术演进

第4篇： 深度强化学习十大原则

第3篇： “超参数”自动化设置方法---DeepHyper

第2篇： 深度强化学习的加速方法

第1篇： 深入浅出解读"多巴胺（Dopamine）论文"、环境配置和实例分析

第11期论文：2019-12-19(3篇，一篇OpennAI,一篇Nvidia)

第10期论文：2019-12-13(8篇)

第9期论文：2019-12-3(3篇)

第8期论文：2019-11-18(5篇)

第7期论文：2019-11-15(6篇)

第6期论文：2019-11-08(2篇)

第5期论文：2019-11-07(5篇，一篇DeepMind发表)

第4期论文：2019-11-05(4篇)

第3期论文：2019-11-04(6篇)

第2期论文：2019-11-03(3篇)

第1期论文：2019-11-02(5篇)