Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixes wrong reference extra PG proof 1 #373

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fixes wrong reference extra PG proof 1 #373

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3811330
Fixes wrong reference
datajanko Sep 16, 2022
dd7a8e5
Update rl_intro3.rst
datajanko Sep 16, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions docs/spinningup/rl_intro3.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -338,9 +338,8 @@ is called the **reward-to-go** from that point, and this policy gradient express

**But how is this better?** A key problem with policy gradients is how many sample trajectories are needed to get a low-variance sample estimate for them. The formula we started with included terms for reinforcing actions proportional to past rewards, all of which had zero mean, but nonzero variance: as a result, they would just add noise to sample estimates of the policy gradient. By removing them, we reduce the number of sample trajectories needed.

An (optional) proof of this claim can be found `here`_, and it ultimately depends on the EGLP lemma.
An (optional) proof of this claim can be found `here <../spinningup/extra_pg_proof1.html>`_, and it ultimately depends on the EGLP lemma.

.. _`here`: ../spinningup/extra_pg_proof1.html

Implementing Reward-to-Go Policy Gradient
=========================================
Expand Down Expand Up @@ -474,4 +473,4 @@ In this chapter, we described the basic theory of policy gradient methods and co
.. _`advantage of an action`: ../spinningup/rl_intro.html#advantage-functions
.. _`this page`: ../spinningup/extra_pg_proof2.html
.. _`Generalized Advantage Estimation`: https://arxiv.org/abs/1506.02438
.. _`Vanilla Policy Gradient`: ../algorithms/vpg.html
.. _`Vanilla Policy Gradient`: ../algorithms/vpg.html