强化学习是目前热门的研究方向。对不同强化学习的方法与paper进行分类有助于我们进一步了解针对不同的应用场景，如何使用合适的强化学习方法。本文将对强化学习进行分类并列出对应的paper。
11. Imitation Learning and Inverse Reinforcement Learning系列
算法名称：Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy
论文标题：Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy
发表会议：Carnegie Mellon University
论文链接：http://www.cs.cmu.edu/~bziebart/publications/thesis-bziebart.pdf
当前谷歌学术引用次数：291
算法名称：GCL
论文标题：Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
发表会议：ICML, 2016
论文链接：https://arxiv.org/abs/1603.00448
当前谷歌学术引用次数：538
算法名称：GAIL
论文标题：Generative Adversarial Imitation Learning
发表会议：NIPS, 2016
论文链接：https://arxiv.org/abs/1606.03476
当前谷歌学术引用次数：1194
算法名称：DeepMimic
论文标题：DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
发表会议：ACM Transactions on Graphics (TOG), 2018
论文链接：https://xbpeng.github.io/projects/DeepMimic/2018_TOG_DeepMimic.pdf
当前谷歌学术引用次数：354
--
算法名称：VAIL
论文标题：Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
发表会议：ICLR, 2019
论文链接：https://arxiv.org/abs/1810.00821
当前谷歌学术引用次数：95
算法名称：MetaMimic
论文标题：One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
发表会议：Arxiv
论文链接：https://arxiv.org/abs/1810.05017
当前谷歌学术引用次数：12
12. Reproducibility, Analysis, and Critique系列
算法名称：rllab
论文标题：Benchmarking Deep Reinforcement Learning for Continuous Control
发表会议：ICML, 2016
论文链接：https://arxiv.org/abs/1604.06778
当前谷歌学术引用次数：1106
算法名称：Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
论文标题：Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
发表会议：ICML, 2017
论文链接：https://arxiv.org/abs/1708.04133
当前谷歌学术引用次数：149
算法名称：Deep Reinforcement Learning that Matters
论文标题：Deep Reinforcement Learning that Matters
发表会议：AAAI, 2018
论文链接：https://arxiv.org/abs/1709.06560
当前谷歌学术引用次数：852
算法名称：Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
论文标题：Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
发表会议：European Workshop on Reinforcement Learning, 2018
论文链接：https://arxiv.org/abs/1810.02525
当前谷歌学术引用次数：8
算法名称：Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
论文标题：Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
发表会议：CoRR, 2018
论文链接：https://openreview.net/forum?id=qGJDBwwhFTN
当前谷歌学术引用次数：47
算法名称：Simple Random Search Provides a Competitive Approach to Reinforcement Learning
论文标题：Simple Random Search Provides a Competitive Approach to Reinforcement Learning
发表会议：NIPS, 2018
论文链接：https://arxiv.org/abs/1803.07055
当前谷歌学术引用次数：195
算法名称：Benchmarking Model-Based Reinforcement Learning
论文标题：Benchmarking Model-Based Reinforcement Learning
发表会议：NIPS, 2018
论文链接：https://arxiv.org/abs/1907.02057
当前谷歌学术引用次数：95
13. Bonus: Classic Papers in RL Theory or Review系列
算法名称：Policy Gradient Methods for Reinforcement Learning with Function Approximation
论文标题：Policy Gradient Methods for Reinforcement Learning with Function Approximation
发表会议：NIPS, 1999
论文链接：https://papers.nips.cc/paper/1713-policy-gradient-methods-for-reinforcement-learning-with-function-approximation.pdf
当前谷歌学术引用次数：4152
算法名称：An Analysis of Temporal-Difference Learning with Function Approximation
论文标题：An Analysis of Temporal-Difference Learning with Function Approximation
发表会议：IEEE transactions on automatic control, 1997
论文链接：http://web.mit.edu/jnt/www/Papers/J063-97-bvr-td.pdf
当前谷歌学术引用次数：1302
算法名称：Reinforcement Learning of Motor Skills with Policy Gradients
论文标题：Reinforcement Learning of Motor Skills with Policy Gradients
发表会议：Neural networks, 2008
论文链接：http://www.kyb.mpg.de/fileadmin/user_upload/files/publications/attachments/Neural-Netw-2008-21-682_4867%5b0%5d.pdf
当前谷歌学术引用次数：911
算法名称：Approximately Optimal Approximate Reinforcement Learning
论文标题：Approximately Optimal Approximate Reinforcement Learning
发表会议：ICML, 2002
论文链接：https://people.eecs.berkeley.edu/~pabbeel/cs287-fa09/readings/KakadeLangford-icml2002.pdf
当前谷歌学术引用次数：516
算法名称：A Natural Policy Gradient
论文标题：A Natural Policy Gradient
发表会议：NIPS, 2001
论文链接：https://papers.nips.cc/paper/2073-a-natural-policy-gradient.pdf
当前谷歌学术引用次数：844
算法名称：Algorithms for Reinforcement Learning
论文标题：Algorithms for Reinforcement Learnin
发表会议：ICML, 2010
论文链接：https://sites.ualberta.ca/~szepesva/papers/RLAlgsInMDPs.pdf
当前谷歌学术引用次数：1152
