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

Add docs for evaluation #2151

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

Add docs for evaluation #2151

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9316a61
Add docs for evaluation
yeukfu Oct 22, 2020
fd2bef3
Update docs
yeukfu Oct 28, 2020
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
1 change: 1 addition & 0 deletions docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ and how to implement new MDPs and new algorithms.
user/concept_experiment
user/sampling
user/logging_plotting
user/evaluation

.. toctree::
:maxdepth: 2
Expand Down
31 changes: 31 additions & 0 deletions docs/user/evaluation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# Evaluation

garage provides two useful function to evaluate the performance of an
algorithm, [log_performance](../_autoapi/garage/index.html#garage.log_performance)
and [log_multitask_performance](../_autoapi/garage/index.html#garage.log_multitask_performance).
`log_performance` is used for single-task algorithms, while
`log_multitask_performance` is used for multi-task algorithms.

The input of the both functions is [EpisodeBatch](../_autoapi/garage/index.html#garage.EpisodeBatch),
which is a batch of episodes.

These functions will evaluate algorithms in from the following aspects:

- `AverageReturn`: The average return (sum of rewards in an episode) of all
episodes.

- `AverageDiscountedReturn`: The average discounted return of all episodes.

- `StdReturn`: The standard deviation of undiscounted returns.

- `MaxReturn`: The maximum undiscounted return.

- `MinReturn`: The minimum undiscounted return.

- `TerminationRate`: Terminated episodes / all episodes.

- `SuccessRate` (if applicable): The rate of success among all episodes.

----

*This page was authored by Ruofu Wang ([@yeukfu](https://github.com/yeukfu)).*