导语: 国际人工智能联合会议(International Joint Conference on Artificial Intelligence, 简称为 IJCAI)是人工智能领域中最主要的学术会议之一,原为单数年召开,自2016年起改为每年召开。因疫情的影响, IJCAI 2020将于2021年1月5日-10日在举行。 根据AMiner-IJCAI 2020词云图,小脉发现表征学习、图神经网络、深度强化学习、深度神经网络等都是今年比较火的Topic,受到了很多人的关注。今天小脉给大家分享的是IJCAI 2020七篇必读的深度强化学习(Deep Reinforcement Learning)相关论文。 1. 论文名称:Efficient Deep Reinforcement Learning via Adaptive Policy Transfer论文链接:https://www.aminer.cn/pub/5ef96b048806af6ef2772111/efficient-deep-reinforcement-learning-via-adaptive-policy-transfer?conf=ijcai2020作者:Tianpei Yang、Jianye Hao、Zhaopeng Meng、Zongzhang Zhang、Yujing Hu、Yingfeng Chen、Changjie Fan、Weixun Wang、Wulong Liu、Zhaodong Wang、Jiajie Peng简介:· The authors propose a Policy Transfer Framework (PTF) which can efficiently select the optimal source policy and exploit the useful information to facilitate the target task learning. · PTF efficiently avoids negative transfer through terminating the exploitation of current source policy and selects another one adaptively. · PTF can be combined with existing deep DRL methods. · Experimental results show PTF efficiently accelerates the learning process of existing state-ofthe-art DRL methods and outperforms previous policy reuse approaches. 2. 论文名称:KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge论文链接:https://www.aminer.cn/pub/5e4d083f3a55ac8cfd770c23/kogun-accelerating-deep-reinforcement-learning-via-integrating-human-suboptimal-knowledge?conf=ijcai2020作者:Zhang Peng、Jianye Hao、Wang Weixun、Tang Hongyao、Ma Yi、Duan Yihai、Zheng Yan简介:· The authors propose a novel policy network framework called KoGuN to leverage human knowledge to accelerate the learning process of RL agents. · The authors firstly evaluate the algorithm on four tasks in Section 4.1 : CartP ole [Barto and Sutton, 1982], LunarLander and LunarLanderContinuous in OpenAI Gym [Brockman et al, 2016] and F lappyBird in PLE [Tasfi, 2016]. · The authors show the effectiveness and robustness of KoGuN in sparse reward setting in Section 4.2. · For PPO without KoGuN, the authors use a neural network with two full-connected hidden layers as policy approximator. · For KoGuN with normal network (KoGuN-concat) as refine module, the authors use a neural network with two full-connected hidden layers for the refine module. · For KoGuN with hypernetworks (KoGuN-hyper), the authors use hypernetworks to generate a refine module with one hidden layer. · All hidden layers described above have 32 units. w1 is set to 0.7 at beginning and decays to 0.1 in the end of training phase 3. 论文名称:Generating Behavior-Diverse Game AIs with Evolutionary Multi-Objective Deep Reinforcement Learning论文链接:https://www.aminer.cn/pub/5ef96b048806af6ef277219d/generating-behavior-diverse-game-ais-with-evolutionary-multi-objective-deep-reinforcement-learning?conf=ijcai2020作者:Ruimin Shen、Yan Zheng、Jianye Hao、Zhaopeng Meng、Yingfeng Chen、Changjie Fan、Yang Liu简介:· This paper proposes EMOGI, aiming to efficiently generate behavior-diverse Game AIs by leveraging EA, PMOO and DRL. · Empirical results show the effectiveness of EMOGI in creating diverse and complex behaviors. · To deploy AIs in commercial games, the robustness of the generated AIs is worth investigating as future work [Sun et al, 2020] 4. 论文名称:Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning论文链接:https://www.aminer.cn/pub/5eda19d991e01187f5d6db49/solving-hard-ai-planning-instances-using-curriculum-driven-deep-reinforcement-learning?conf=ijcai2020作者:Feng Dieqiao、Gomes Carla P.、Selman Bart简介:· The authors presented a framework based on deep RL for solving hard combinatorial planning problems in the domain of Sokoban. · The authors showed the effectiveness of the learning based planning strategy by solving hard Sokoban instances that are out of reach of previous search-based solution techniques, including methods specialized for Sokoban. · Since Sokoban is one of the hardest challenge domains for current AI planners, this work shows the potential of curriculumbased deep RL for solving hard AI planning tasks. 5. 论文名称:I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations论文链接:https://www.aminer.cn/pub/5ef96b048806af6ef2772128/i-r-promoting-deep-reinforcement-learning-by-the-indicator-for-expressive-representations?conf=ijcai2020作者:Xufang Luo、Qi Meng、Di He、Wei Chen、Yunhong Wang简介:· The authors mainly study the relationship between representations and performance of the DRL agents. · The authors define the NSSV indicator, i.e, the smallest number of significant singular values, as a measurement for learning representations, the authors verify the positive correlation between NSSV and the rewards, and further propose a novel method called I4R, to improve DRL algorthims via adding the corresponding regularization term to enhance NSSV. · The authors show the proposed method I4R based on exploratory experiments, including 3 parts, i.e., observations, the proposed indicator NSSV, and the novel algorithm I4R. 6. 论文名称:Rebalancing Expanding EV Sharing Systems with Deep Reinforcement Learning论文链接:https://www.aminer.cn/pub/5ef96b048806af6ef2772092/rebalancing-expanding-ev-sharing-systems-with-deep-reinforcement-learning?conf=ijcai2020作者:Man Luo、Wenzhe Zhang、Tianyou Song、Kun Li、Hongming Zhu、Bowen Du 、Hongkai Wen简介:· The authors study the incentive-based rebalancing for continuous expanding EV sharing systems. · The authors design a simulator to simulate the operation of EV sharing systems, which is calibrated with real data from an actual EV sharing system for a year. · Extensive experiments have shown that the proposed approach significantly outperforms the baselines and state-of-the-art in both satisfied demand rate and net revenue, and is robust to different levels of system expansion dynamics. · The authors show that the proposed approach performs consistently with different charging time and EV range. 7. 论文名称:Independent Skill Transfer for Deep Reinforcement Learning论文链接:https://www.aminer.cn/pub/5ef96b048806af6ef2772129/independent-skill-transfer-for-deep-reinforcement-learning?conf=ijcai2020作者:Qiangxing Tian、Guanchu Wang、Jinxin Liu、Donglin Wang、Yachen Kang简介:· Deep reinforcement learning (DRL) has wide applications in various challenging fields, such as real-world visual navigation [Zhu et al, 2017], playing games [Silver et al, 2016] and robotic controls [Schulman et al, 2015] · In this work , the authors propose to learn independent skills for efficient skill transfer, where the learned primitive skills with strong correlation are decomposed into independent skills · We take the eigenvalues in Figure 1 as an example: for the case of 6 primitive skills, |Z| = 3 is reasonable since more than 98% component of primitive actions can be represented by three independent components · Effective observation collection and independent skills guarantee the success of low-dimension skill transfer 查看更多IJCAI 2020精彩论文,请移步:https://www.aminer.cn/conf/ijcai2020/papers添加“小脉”微信,留言“IJCAI 2020”,即可加入【IJCAI 2020会议交流群】,与IJCAI 2020论文作者面对面沟通! 点击阅读原文,查看更多精彩! 喜欢本篇内容,请分享、点赞、在看