Xiaohu Zhu

I think ddpg can be added, this algorithm performs better for continuous action space. Look forward. :)

https://arxiv.org/pdf/1703.01703.pdf

FeUdal Networks for Hierarchical Reinforcement Learning https://arxiv.org/pdf/1703.01161.pdf

Neural Fictitious Self Play NFSP

1

Neural Fictitious Self Play https://arxiv.org/abs/1603.01121

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep RL https://arxiv.org/pdf/1706.00387.pdf

[zh] cs-229-linear-algebra

1

linear algebra part is finished.

[zh] cs-229-probability

1

probability part is finished.

small fix