probml / pml2-book

Probabilistic Machine Learning: Advanced Topics
MIT License
1.4k stars 119 forks source link

slightly expand description of DDPG in sec 35.3.5 #323

Closed murphyk closed 3 months ago

murphyk commented 4 months ago

Currently it just says "The DDPG algorithm of [Lil+16], which stands for “deep deterministic policy gradient”, uses the DQN method (Section 35.2.6) to update Q that is represented by deep neural networks. " We expand on this a little bit.