【5分钟 Paper】Deterministic Policy Gradient Algorithms

简介: 【5分钟 Paper】Deterministic Policy Gradient Algorithms
  • 论文题目:Deterministic Policy Gradient Algorithms

所解决的问题?

  stochastic policy的方法由于含有部分随机,所以效率不高,方差大,采用deterministic policy方法比stochastic policy采样效率高,但是没有办法探索环境,因此只能采用off-policy的方法来进行了。

背景

  以往的action是一个动作分布π θ ( a ∣ s ),作者所提出的是输出一个确定性的策略(deterministic policy) a = μ θ ( s )

   In the stochastic case,the policy gradient integrates over both state and action spaces, whereas in the deterministic case it only integrates over the state space.

  • Stochastic Policy Gradient

   前人采用off-policy的随机策略方法, behaviour policyβ ( a ∣ s ) ≠ π

image.png

  Differentiating the performance objective and applying an approximation gives the off-policy policy-gradient (Degris et al., 2012b)


image.png

所采用的方法?


  • On-Policy Deterministic Actor-Critic

  如果环境有大量噪声帮助智能体做exploration的话,这个算法还是可以的,使用sarsa更新critic,使用 Q w ( s , a ) 近似true action-valueQ μ


image.png

  • Off-Policy Deterministic Actor-Critic

  we modify the performance objective to be the value function of the target policy, averaged over the state distribution of the behaviour policy

image.png


 得到off-policy deterministic actorcritic (OPDAC) 算法:


image.png


 与stochastic off policy算法不同的是由于这里是deterministic policy,所以不需要用重要性采样(importance sampling)。


取得的效果?

20200302145247712.png


所出版信息?作者信息?


  这篇文章是ICML2014上面的一篇文章。第一作者David SilverGoogle DeepMindresearch Scientist,本科和研究生就读于剑桥大学,博士于加拿大阿尔伯特大学就读,2013年加入DeepMind公司,AlphaGo创始人之一,项目领导者。

20200301211515431.jpg



参考链接


  • 参考文献:Degris, T., White, M., and Sutton, R. S. (2012b). Linear off-policy actor-critic. In 29th International Conference on Machine Learning.


扩展阅读

image.png

 最后,论文给出了DPG的采用线性函数逼近定理,以及一些理论证明基础。

  • 参考文献:Sutton, R.S., McAllester D. A., Singh, S. P., and Mansour, Y. (1999). Policy gradient methods for reinforcement learning with function approximation. In Neural Information Processing Systems 12, pages 1057–1063.


  这篇文章以后有时间再读一遍吧,里面还是有些证明需要仔细推敲一下

相关文章
|
2月前
|
算法 数据挖掘
文献解读-Consistency and reproducibility of large panel next-generation sequencing: Multi-laboratory assessment of somatic mutation detection on reference materials with mismatch repair and proofreading deficiency
Consistency and reproducibility of large panel next-generation sequencing: Multi-laboratory assessment of somatic mutation detection on reference materials with mismatch repair and proofreading deficiency,大panel二代测序的一致性和重复性:对具有错配修复和校对缺陷的参考物质进行体细胞突变检测的多实验室评估
26 6
文献解读-Consistency and reproducibility of large panel next-generation sequencing: Multi-laboratory assessment of somatic mutation detection on reference materials with mismatch repair and proofreading deficiency
|
PyTorch 算法框架/工具
Pytorch中Trying to backward through the graph和one of the variables needed for gradient错误解决方案
Pytorch中Trying to backward through the graph和one of the variables needed for gradient错误解决方案
2058 0
Pytorch中Trying to backward through the graph和one of the variables needed for gradient错误解决方案
|
算法 计算机视觉 知识图谱
ACL2022:A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction
少样本关系提取旨在通过在每个关系中使用几个标记的例子进行训练来预测句子中一对实体的关系。最近的一些工作引入了关系信息
122 0
|
算法 PyTorch 算法框架/工具
论文解读:LaMa:Resolution-robust Large Mask Inpainting with Fourier Convolutions
论文解读:LaMa:Resolution-robust Large Mask Inpainting with Fourier Convolutions
644 0
|
12月前
|
机器学习/深度学习 算法
尝试理解论文SPOT1的代码1:Supported Policy Optimization for Offline Reinforcement Learning
尝试理解论文SPOT1的代码1:Supported Policy Optimization for Offline Reinforcement Learning
131 0
|
机器学习/深度学习 存储 分布式计算
【深度学习系列】(二)--An overview of gradient descent optimization algorithms
【深度学习系列】(二)--An overview of gradient descent optimization algorithms
149 0
【深度学习系列】(二)--An overview of gradient descent optimization algorithms
|
机器学习/深度学习 自然语言处理 PyTorch
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
问题 B: Scaling Recipe
你有一个食谱,其中指定了一些食材,你需要的每种食材的数量,以及它产生的分量。但是,你需要的份量和食谱中指定的份量不一样!你如何衡量它?
100 0