dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Better guide

Browse Source
This commit is contained in:
Dominik Moritz Roth 2023-12-13 15:50:13 +01:00
parent 57c3d36490
commit ddd0eaf88a
4 changed files with 17 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
docs/source/guide/basic_usage.rst
View File

@ -1,9 +1,7 @@
Basic Usage Basic Usage
----------- -----------
We will only show the basics here and prepared `multiple We will only show the basics here and prepared :ref:`multiple examples <example-general>` for a more detailed look.
examples <https://github.com/ALRhub/fancy_gym/tree/master/fancy_gym/examples/>`__
for a more detailed look.
Step-Based Environments Step-Based Environments
~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~
@ -34,7 +32,7 @@ Regular step based environments added by Fancy Gym are added into the
if terminated or truncated: if terminated or truncated:
observation, info = env.reset() observation, info = env.reset()
Black-box Environments Black-Box Environments
~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~
All environments provide by default the cumulative episode reward, this All environments provide by default the cumulative episode reward, this
@ -67,13 +65,13 @@ a MP-variant of an environment is given by
``<original namespace>_<MP name>/``. Just keep in mind, calling ``<original namespace>_<MP name>/``. Just keep in mind, calling
``step()`` executes a full trajectory. ``step()`` executes a full trajectory.
| **Note:** .. note::
| Currently, we are also in the process of enabling replanning as Currently, we are also in the process of enabling replanning as
well as learning of sub-trajectories. This allows to split the well as learning of sub-trajectories. This allows to split the
episode into multiple trajectories and is a hybrid setting between episode into multiple trajectories and is a hybrid setting between
step-based and black-box leaning. While this is already step-based and black-box leaning. While this is already
implemented, it is still in beta and requires further testing. Feel implemented, it is still in beta and requires further testing. Feel
free to try it and open an issue with any problems that occur. free to try it and open an issue with any problems that occur.
.. code:: python .. code:: python

18
docs/source/guide/episodic_rl.rst
View File

@ -3,7 +3,7 @@ What is Episodic RL?
.. raw:: html .. raw:: html
<p align="justify"> <div class="justify">
Movement primitive (MP) environments differ from traditional step-based Movement primitive (MP) environments differ from traditional step-based
environments. They align more with concepts from stochastic search, environments. They align more with concepts from stochastic search,
@ -14,13 +14,6 @@ produced by trajectory generators like Dynamic Movement Primitives
(DMP), Probabilistic Movement Primitives (ProMP) or Probabilistic (DMP), Probabilistic Movement Primitives (ProMP) or Probabilistic
Dynamic Movement Primitives (ProDMP). Dynamic Movement Primitives (ProDMP).
.. raw:: html
</p>
.. raw:: html
<p align="justify">
Once generated, these trajectories are converted into step-by-step Once generated, these trajectories are converted into step-by-step
actions using a trajectory tracking controller. The specific controller actions using a trajectory tracking controller. The specific controller
@ -29,13 +22,6 @@ position, velocity, and PD-Controllers tailored for position, velocity,
and torque control. Additionally, we have a specialized controller and torque control. Additionally, we have a specialized controller
designed for the MetaWorld control suite. designed for the MetaWorld control suite.
.. raw:: html
</p>
.. raw:: html
<p align="justify">
While the overarching objective of MP environments remains the learning While the overarching objective of MP environments remains the learning
of an optimal policy, the actions here represent the parametrization of of an optimal policy, the actions here represent the parametrization of
@ -47,4 +33,4 @@ every unique context.
.. raw:: html .. raw:: html
</p> </div>

9
docs/source/guide/installation.rst
View File

@ -1,10 +1,11 @@
Installation Installation
------------ ------------
We recommend installing ``fancy_gym`` into a virtual environment as .. note::
provided by `venv <https://docs.python.org/3/library/venv.html>`__. 3rd We recommend installing ``fancy_gym`` into a virtual environment as
party alternatives to venv like `Poetry <https://python-poetry.org/>`__ provided by `venv <https://docs.python.org/3/library/venv.html>`__. 3rd
or `Conda <https://docs.conda.io/en/latest/>`__ can also be used. party alternatives to venv like `Poetry <https://python-poetry.org/>`__
or `Conda <https://docs.conda.io/en/latest/>`__ can also be used.
Installation from PyPI (recommended) Installation from PyPI (recommended)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

2
docs/source/guide/upgrading_envs.rst
View File

@ -92,7 +92,7 @@ If you created a new task wrapper, feel free to open a PR, so we can
integrate it for others to use as well. Without the integration the task integrate it for others to use as well. Without the integration the task
can still be used. A rough outline can be shown here, for more details can still be used. A rough outline can be shown here, for more details
we recommend having a look at the we recommend having a look at the
`examples <https://github.com/ALRhub/fancy_gym/tree/master/fancy_gym/examples/>`__. :ref:`multiple examples <example-mp>`.
If the step-based is already registered with gym, you can simply do the If the step-based is already registered with gym, you can simply do the
following: following: