<![CDATA[深度强化学习实验室：一个“开源开放、共享共进”的强化学习学术组织。]]>

<![CDATA[深度强化学习实验室：一个“开源开放、共享共进”的强化学习学术组织。]]>https://blog.csdn.net/deeprlzh-cnhttps://blog.csdn.net/<![CDATA[【总结】为什么对累积奖励减去baseline项能起到减小方差的作用？]]>https://blog.csdn.net/deeprl/article/details/119902039https://blog.csdn.net/deeprl/article/details/119902039deeprlTue, 24 Aug 2021 08:26:35 +0800<![CDATA[【模仿学习】南京大学&港中文联合总结: 29页中文详述模仿学习完整过程]]>https://blog.csdn.net/deeprl/article/details/119814483https://blog.csdn.net/deeprl/article/details/119814483deeprlThu, 19 Aug 2021 09:54:34 +0800<![CDATA[【重磅总结】170道强化学习面试题目汇总，助力实验室RLer冲刺求职季！]]>https://blog.csdn.net/deeprl/article/details/119621650https://blog.csdn.net/deeprl/article/details/119621650deeprlWed, 11 Aug 2021 08:37:38 +0800<![CDATA[【Mava】一个分布式多智能体强化学习研究框架]]>https://blog.csdn.net/deeprl/article/details/119259582https://blog.csdn.net/deeprl/article/details/119259582deeprlFri, 30 Jul 2021 08:03:10 +0800<![CDATA[CORL: 基于变量序和强化学习的因果发现算法]]>https://blog.csdn.net/deeprl/article/details/119194518https://blog.csdn.net/deeprl/article/details/119194518deeprlWed, 28 Jul 2021 14:49:41 +0800<![CDATA[【Peter Dayan】自然和人工强化学习的结合、以及未来的发展方向]]>https://blog.csdn.net/deeprl/article/details/119048016https://blog.csdn.net/deeprl/article/details/119048016deeprlFri, 23 Jul 2021 10:47:33 +0800<![CDATA[【Google最新成果】使用新的物理模拟引擎加速强化学习]]>https://blog.csdn.net/deeprl/article/details/118837165https://blog.csdn.net/deeprl/article/details/118837165deeprlFri, 16 Jul 2021 09:45:58 +0800<![CDATA[【最新】如何降低深度强化学习研究的计算成本(Reducing the Computational Cost of DeepRL)...]]>https://blog.csdn.net/deeprl/article/details/118742252https://blog.csdn.net/deeprl/article/details/118742252deeprlWed, 14 Jul 2021 09:39:34 +0800<![CDATA[【ICML2021】 9篇RL论文作者汪昭然：构建“元宇宙”和理论基础，让深度强化学习从虚拟走进现实...]]>https://blog.csdn.net/deeprl/article/details/118715894https://blog.csdn.net/deeprl/article/details/118715894deeprlTue, 13 Jul 2021 08:48:42 +0800<![CDATA[【DRL4IR】SIGIR'21 -第二届信息检索深度强化学习研讨会(7月15-1)]]>https://blog.csdn.net/deeprl/article/details/118715673https://blog.csdn.net/deeprl/article/details/118715673deeprlTue, 13 Jul 2021 08:48:42 +0800<![CDATA[ICML RL4RealLife｜聚焦强化学习落地难题，学术与商业巨头齐聚【7月23日，不见不散】...]]>https://blog.csdn.net/deeprl/article/details/118503015https://blog.csdn.net/deeprl/article/details/118503015deeprlMon, 05 Jul 2021 17:40:52 +0800<![CDATA[强化学习 | 基于Novelty-Pursuit的高效探索方法]]>https://blog.csdn.net/deeprl/article/details/118005672https://blog.csdn.net/deeprl/article/details/118005672deeprlThu, 17 Jun 2021 10:13:24 +0800<![CDATA[【华为诺亚方舟实验室】2022届毕业生招聘--决策(强化学习)推理方向]]>https://blog.csdn.net/deeprl/article/details/117858185https://blog.csdn.net/deeprl/article/details/117858185deeprlSat, 12 Jun 2021 10:20:49 +0800<![CDATA[【Reward is enough】Sutton、DavidSilver师徒联手：奖励机制足够实现各种目标。]]>https://blog.csdn.net/deeprl/article/details/117829616https://blog.csdn.net/deeprl/article/details/117829616deeprlFri, 11 Jun 2021 08:58:42 +0800<![CDATA[【重磅最新】163篇ICML-2021强化学习领域论文整理汇总(2021.06.07)]]>https://blog.csdn.net/deeprl/article/details/117678353https://blog.csdn.net/deeprl/article/details/117678353deeprlMon, 07 Jun 2021 07:55:28 +0800<![CDATA[【Easy-RL】中科院-清华-北大3位作者贡献的200页强化学习总结笔记]]>https://blog.csdn.net/deeprl/article/details/117236826https://blog.csdn.net/deeprl/article/details/117236826deeprlMon, 24 May 2021 10:04:35 +0800<![CDATA[京东 | AI人才联合培养计划（NLP项目实战）]]>https://blog.csdn.net/deeprl/article/details/117050678https://blog.csdn.net/deeprl/article/details/117050678deeprlWed, 19 May 2021 14:36:02 +0800<![CDATA[【重磅推荐: 强化学习课程】清华大学李升波老师《强化学习与控制》]]>https://blog.csdn.net/deeprl/article/details/116811400https://blog.csdn.net/deeprl/article/details/116811400deeprlFri, 14 May 2021 09:36:59 +0800<![CDATA[【拒绝内卷】狼吃羊的AI奖励机制不合理：内卷，如何解决？]]>https://blog.csdn.net/deeprl/article/details/115038270https://blog.csdn.net/deeprl/article/details/115038270deeprlSat, 20 Mar 2021 16:39:37 +0800<![CDATA[【重磅推荐】哥大开源“FinRL”: 一个用于量化金融自动交易的深度强化学习库]]>https://blog.csdn.net/deeprl/article/details/114828024https://blog.csdn.net/deeprl/article/details/114828024deeprlMon, 15 Mar 2021 08:05:44 +0800