• Zihan Ding* - Princeton University (zhding[at]
  • Hao Dong - Peking University


Previous chapters have provided the readers the main knowledge of deep reinforcement learning, main categories of reinforcement learning algorithms as well as their code implementations, and several practical projects for better understanding deep reinforcement learning in practice. However, due to the aforementioned challenges like low sample efficiency, instability and so on, it may still be hard for the novices to employ those algorithms well in their own applications. So in this chapter, we summarize some common tricks and methods in detail, either mathematically or empirically for deep reinforcement learning applications in practice. The methods and tips are provided from both the stage of algorithm implementation and the stage of training and debugging, to avoid the readers from getting trapped in some practical difficulties. These empirical tricks can be significantly effective in some cases, but not always. This is due to the complexity and sensitivity of deep reinforcement learning models, where sometimes an ensemble of tricks needs to be applied. People can also refer to this chapter to get some enlightenment of solutions when getting stuck on the projects.

Keywords: deep reinforcement learning, application, implementation, reward engineering, neural network, normalization, efficiency, stability


To cite this book, please use this bibtex entry:

 title={Tricks of Implementation},
 author={Zihan Ding, Hao Dong},
 editor={Hao Dong, Zihan Ding, Shanghang Zhang},
 booktitle={Deep Reinforcement Learning: Fundamentals, Research, and Applications},
 publisher={Springer Nature},

If you find any typos or have suggestions for improving the book, do not hesitate to contact with the corresponding author (name with *).