- Thesis title : Continuous Control With Deep Reinforcement Learning
The problem solved?
This article will be Deep Q-Learning
applied to the Deterministic Policy Gradient
algorithm. If you know DPG
, then this article is to introduce DQN
improved a bit DPG
of state value function
. It solves the limitation of the DQN
need to find maximizes action-value
only the discrete action space.
background
In fact, it is a combination of these two articles:
- 【5分钟 Paper】Playing Atari with Deep Reinforcement Learning
- 【5分钟 Paper】Deterministic Policy Gradient Algorithms
The method used?
This DDPG
I too familiar, I really do not want to write what the appendix it a pseudo-code:
The effect achieved?
The experimental results are shown below:
Information published? author information?
This article is the one ICLR2016
above. The first author TimothyP.Lillicrap
is Google DeepMind
of research Scientist
.
Research focuses on machine learning and statistics for optimal control and decision making, as well as using these mathematical frameworks to understand how the brain learns. In recent work, I’ve developed new algorithms and approaches for exploiting deep neural networks in the context of reinforcement learning, and new recurrent memory architectures for one-shot learning. Applications of this work include approaches for recognizing images from a single example, visual question answering, deep learning for robotics problems, and playing games such as Go and StarCraft. I’m also fascinated by the development of deep network models that might shed light on how robust feedback control laws are learned and employed by the central nervous system.
- Personal homepage: http://contrastiveconvergence.net/~timothylillicrap/index.php
My micro-channel public number Name : deep learning and advanced intelligent decision-making
micro-channel public number ID : MultiAgent1024
Public Number Description : The main share deep learning, computer games, reinforcement learning, and other related content! Looking forward to your attention, welcome to learn and exchange progress together!