Total stochastic gradient algorithms and applications in reinforcement learning
arXiv:1902.01722
Abstract
Backpropagation and the chain rule of derivatives have been prominent; however, the total derivative rule has not enjoyed the same amount of attention. In this work we show how the total derivative rule leads to an intuitive visual framework for creating gradient estimators on graphical models. In particular, previous "policy gradient theorems" are easily derived. We derive new gradient estimators based on density estimation, as well as a likelihood ratio gradient, which "jumps" to an intermediate node, not directly to the objective function. We evaluate our methods on model-based policy gradient algorithms, achieve good performance, and present evidence towards demystifying the success of the popular PILCO algorithm.
NeurIPS 2018
Cited by in corpus (4)
- Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
- FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching
- A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme
- GO Hessian for Expectation-Based Objectives