A few lessons learned in reinforcement learning for quadcopter attitude control

Explore this paper's citation graph

Summary

This paper discusses theoretical as well as practical aspects of training neural nets for controlling a crazyflie 2.0 drone, and describes thoroughly the choices in training algorithms, neural net architecture, hyperparameters, observation space etc.

Type
preprint
Published
2021-05-19
Cited by
21
References
54
Access
Open access

Keywords

Quadcopter, Reinforcement learning, Computer science, Robustness (evolution), Artificial intelligence

References

Cited by

Related papers