Stable-Baselines3 v1.0 (#354)

* Bump version and update doc

* Fix name

* Apply suggestions from code review

Co-authored-by: Adam Gleave <adam@gleave.me>

* Update docs/index.rst

Co-authored-by: Adam Gleave <adam@gleave.me>

* Update wording for RL zoo

Co-authored-by: Adam Gleave <adam@gleave.me>

README.md

@@ -36,7 +36,7 @@ you can take a look at the issues [#48](https://github.com/DLR-RM/stable-baselin
 | Type hints                  | :heavy_check_mark: |
 
 
-### Planned features (v1.1+)
+### Planned features
 
 Please take a look at the [Roadmap](https://github.com/DLR-RM/stable-baselines3/issues/1) and [Milestones](https://github.com/DLR-RM/stable-baselines3/milestones).
 
@@ -48,11 +48,13 @@ A migration guide from SB2 to SB3 can be found in the [documentation](https://st
 
 Documentation is available online: [https://stable-baselines3.readthedocs.io/](https://stable-baselines3.readthedocs.io/)
 
-## RL Baselines3 Zoo: A Collection of Trained RL Agents
+## RL Baselines3 Zoo: A Training Framework for Stable Baselines3 Reinforcement Learning Agents
 
-[RL Baselines3 Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). is a collection of pre-trained Reinforcement Learning agents using Stable-Baselines3.
+[RL Baselines3 Zoo](https://github.com/DLR-RM/rl-baselines3-zoo) is a training framework for Reinforcement Learning (RL).
 
-It also provides basic scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
+It provides scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
+
+In addition, it includes a collection of tuned hyperparameters for common environments and RL algorithms, and agents trained with those settings.
 
 Goals of this repository:
 
@@ -110,9 +112,9 @@ import gym
 
 from stable_baselines3 import PPO
 
-env = gym.make('CartPole-v1')
+env = gym.make("CartPole-v1")
 
-model = PPO('MlpPolicy', env, verbose=1)
+model = PPO("MlpPolicy", env, verbose=1)
 model.learn(total_timesteps=10000)
 
 obs = env.reset()

docs/guide/custom_policy.rst

@@ -13,9 +13,49 @@ and other type of input features (MlpPolicies).
   which handles bounds more correctly.
 
 
+SB3 Policy
+^^^^^^^^^^
 
-Custom Policy Architecture
-^^^^^^^^^^^^^^^^^^^^^^^^^^
+SB3 networks are separated into two mains parts (see figure below):
+
+- A features extractor (usually shared between actor and critic when applicable, to save computation)
+  whose role is to extract features (i.e. convert to a feature vector) from high-dimensional observations, for instance, a CNN that extracts features from images.
+  This is the ``features_extractor_class`` parameter. You can change the default parameters of that features extractor
+  by passing a ``features_extractor_kwargs`` parameter.
+
+- A (fully-connected) network that maps the features to actions/value. Its architecture is controlled by the ``net_arch`` parameter.
+
+
+.. note::
+
+    All observations are first pre-processed (e.g. images are normalized, discrete obs are converted to one-hot vectors, ...) before being fed to the features extractor.
+    In the case of vector observations, the features extractor is just a ``Flatten`` layer.
+
+
+.. image:: ../_static/img/net_arch.png
+
+
+SB3 policies are usually composed of several networks (actor/critic networks + target networks when applicable) together
+with the associated optimizers.
+
+Each of these network have a features extractor followed by a fully-connected network.
+
+.. note::
+
+  When we refer to "policy" in Stable-Baselines3, this is usually an abuse of language compared to RL terminology.
+  In SB3, "policy" refers to the class that handles all the networks useful for training,
+  so not only the network used to predict actions (the "learned controller").
+
+
+
+.. image:: ../_static/img/sb3_policy.png
+
+
+.. .. figure:: https://cdn-images-1.medium.com/max/960/1*h4WTQNVIsvMXJTCpXm_TAw.gif
+
+
+Custom Network Architecture
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 One way of customising the policy network architecture is to pass arguments when creating the model,
 using ``policy_kwargs`` parameter:

docs/guide/developer.rst

@@ -31,6 +31,9 @@ Each algorithm has two main methods:
 - ``.train()`` which updates the parameters using samples from the buffer
 
 
+.. image:: ../_static/img/sb3_loop.png
+
+
 Where to start?
 ===============
 

docs/guide/migration.rst

@@ -98,7 +98,7 @@ Base-class (all algorithms)
 Policies
 ^^^^^^^^
 
-- ``cnn_extractor`` -> ``feature_extractor``, as ``feature_extractor`` in now used with ``MlpPolicy`` too
+- ``cnn_extractor`` -> ``features_extractor``, as ``features_extractor`` in now used with ``MlpPolicy`` too
 
 A2C
 ^^^

docs/guide/rl_zoo.rst

@@ -4,9 +4,11 @@
 RL Baselines3 Zoo
 ==================
 
-`RL Baselines3 Zoo <https://github.com/DLR-RM/rl-baselines3-zoo>`_. is a collection of pre-trained Reinforcement Learning agents using
-Stable-Baselines3.
-It also provides basic scripts for training, evaluating agents, tuning hyperparameters and recording videos.
+`RL Baselines3 Zoo <https://github.com/DLR-RM/rl-baselines3-zoo>`_ is a training framework for Reinforcement Learning (RL).
+
+It provides scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
+
+In addition, it includes a collection of tuned hyperparameters for common environments and RL algorithms, and agents trained with those settings.
 
 Goals of this repository:
 

docs/index.rst

@@ -12,9 +12,9 @@ It is the next major version of `Stable Baselines <https://github.com/hill-a/sta
 
 Github repository: https://github.com/DLR-RM/stable-baselines3
 
-RL Baselines3 Zoo (collection of pre-trained agents): https://github.com/DLR-RM/rl-baselines3-zoo
+RL Baselines3 Zoo (training framework for SB3): https://github.com/DLR-RM/rl-baselines3-zoo
 
-RL Baselines3 Zoo also offers a simple interface to train, evaluate agents and do hyperparameter tuning.
+RL Baselines3 Zoo provides a collection of pre-trained agents, scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
 
 SB3 Contrib (experimental RL code, latest algorithms): https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
 

docs/misc/changelog.rst

@@ -3,13 +3,22 @@
 Changelog
 ==========
 
-Release 1.0rc2 (WIP)
+Release 1.0 (2021-03-15)
 -------------------------------
 
+**First Major Version**
+
 Breaking Changes:
 ^^^^^^^^^^^^^^^^^
 - Removed ``stable_baselines3.common.cmd_util`` (already deprecated), please use ``env_util`` instead
 
+.. warning::
+
+    A refactoring of the ``HER`` algorithm is planned together with support for dictionary observations
+    (see `PR #243 <https://github.com/DLR-RM/stable-baselines3/pull/243>`_ and `#351 <https://github.com/DLR-RM/stable-baselines3/pull/351>`_)
+    This will be a backward incompatible change (model trained with previous version of ``HER`` won't work with the new version).
+
+
 New Features:
 ^^^^^^^^^^^^^
 - Added support for ``custom_objects`` when loading models
@@ -24,7 +33,9 @@ Documentation:
 - Added new project using SB3: rl_reach (@PierreExeter)
 - Added note about slow-down when switching to PyTorch
 - Add a note on continual learning and resetting environment
-
+- Updated RL-Zoo to reflect the fact that is it more than a collection of trained agents
+- Added images to illustrate the training loop and custom policies (created with https://excalidraw.com/)
+- Updated the custom policy section
 
 Pre-Release 0.11.1 (2021-02-27)
 -------------------------------

stable_baselines3/version.txt

@@ -1 +1 @@
-1.0rc2
+1.0