Unverified Commit 3e0d7ad7 authored by OOmotuyi's avatar OOmotuyi Committed by GitHub

Adds figures for manager-based and direct RL environments (#1337)

# Description
Adding reference flow diagram for manager-based and direct RL task
workflows


<!-- As a practice, it is recommended to open an issue to have
discussions on the proposed pull request.
This makes it easier for the community to keep track of what is being
developed or added, and if a given feature
is demanded by more than one party. -->

## Type of change

- Documentation Change



## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

<!--
As you go through the checklist above, you can mark something as done by
putting an x character in it

For example,
- [x] I have done this task
- [ ] I have not done this task
-->

---------
Signed-off-by: 's avatarOOmotuyi <159472067+OOmotuyi@users.noreply.github.com>
parent 9cc298e9
...@@ -36,6 +36,10 @@ or when implementing complex logic that is difficult to decompose into separate ...@@ -36,6 +36,10 @@ or when implementing complex logic that is difficult to decompose into separate
Manager-Based Environments Manager-Based Environments
-------------------------- --------------------------
.. image:: ./Manager-basedTaskWorkflow.jpg
:width: 100%
:alt: Manager-based Task Workflow
A majority of environment implementations follow a similar structure. The environment processes the input actions, A majority of environment implementations follow a similar structure. The environment processes the input actions,
steps through the simulation, computes observations and reward signals, applies randomization, and resets the terminated steps through the simulation, computes observations and reward signals, applies randomization, and resets the terminated
environments. Motivated by this, the environment can be decomposed into individual components that handle each of these tasks. environments. Motivated by this, the environment can be decomposed into individual components that handle each of these tasks.
...@@ -88,6 +92,10 @@ specifications. ...@@ -88,6 +92,10 @@ specifications.
Direct Environments Direct Environments
------------------- -------------------
.. image:: ./Direct-basedTaskWorkflow.jpg
:width: 100%
:alt: Direct-based Task Workflow
The direct-style environment aligns more closely with traditional implementations of environments, The direct-style environment aligns more closely with traditional implementations of environments,
where a single script directly implements the reward function, observation function, resets, and all the other components where a single script directly implements the reward function, observation function, resets, and all the other components
of the environment. This approach does not require the manager classes. Instead, users are provided the complete freedom of the environment. This approach does not require the manager classes. Instead, users are provided the complete freedom
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment