Total Stochastic Gradient Algorithms And Applications In Reinforcement Learning

# Total stochastic gradient algorithms and applications in reinforcement learning

**arXiv ID:** 1902.01722
**Authors:** Paavo Parmas
**Published:** 2019-02-05T14:54:05Z
**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.

## Skill Description

This skill is generated from the arXiv paper: Total stochastic gradient algorithms and applications in reinforcement learning (1902.01722).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1902.01722](http://arxiv.org/abs/1902.01722v1)