docs: enhance the current documentation + gather baselines in separat…

…e folder (#57)

Clean docs - udpate css and create baseline folder in qdax

Co-authored-by: Thomas <t.pierrot@instadeep.com>

README.md

@@ -81,54 +81,6 @@ The QDax library also provides implementations for some useful baseline algorith
 | [NSGA2](https://ieeexplore.ieee.org/document/996017) | [![Open All Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/adaptive-intelligent-robotics/QDax/blob/main/nsga2_spea2_example.ipynb) |
 | [SPEA2](https://www.semanticscholar.org/paper/SPEA2%3A-Improving-the-strength-pareto-evolutionary-Zitzler-Laumanns/b13724cb54ae4171916f3f969d304b9e9752a57f) | [![Open All Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/adaptive-intelligent-robotics/QDax/blob/main/nsga2_spea2_example.ipynb) |
 
-
-## QDax Overview
-
-QDax has been designed to be modular yet flexible so it's easy for anyone to use and extend on the different state-of-the-art QD algortihms available.
-For instance, MAP-Elites is designed to work with a few modular and simple components: `container`, `emitter`, and `scoring_function`.
-
-The `container` specifies the structure of archive of solutions to keep and the addition conditions associated with the archive.
-
-The `emitter` component is responsible for generating new solutions to be evaluated. For example, new solutions can be generated with random mutations, gradient descent, or sampling from distributions as in evolutionary strategies.
-
-The `scoring_function` defines the problem/task we want to solve and functions to evaluate the solutions. For example, the `scoring_function` can be used to represent standard black-box optimization tasks such as rastrigin or RL tasks.
-
-With this modularity, a user can easily swap out any one of the components and pass it to the `MAPElites` class, avoiding having to re-implement all the steps of the algorithm.
-
-Under one layer of abstraction, users have a bit more flexibility. QDax has similarities to the simple and commonly found `ask`/`tell` interface. The `ask` function is similar to the `emit` function in QDax and the `tell` function is similar to the `update` function in QDax. Likewise, the `eval` of solutions is analogous to the `scoring function` in QDax.
-More importantly, QDax handles the archive management which is the key idea of QD algorihtms and not present or needed in standard optimization algorihtms or evolutionary strategies.
-
-```python
-# Initializes repertoire and emitter state
-repertoire, emitter_state, random_key = map_elites.init(init_variables, centroids, random_key)
-
-for i in range(num_iterations):
-
-    # generate new population with the emitter
-    genotypes, random_key = map_elites._emitter.emit(
-        repertoire, emitter_state, random_key
-    )
-
-    # scores/evaluates the population
-    fitnesses, descriptors, extra_scores, random_key = map_elites._scoring_function(
-        genotypes, random_key
-    )
-
-    # update repertoire
-    repertoire = repertoire.add(genotypes, descriptors, fitnesses)
-
-    # update emitter state
-    emitter_state = map_elites._emitter.state_update(
-        emitter_state=emitter_state,
-        repertoire=repertoire,
-        genotypes=genotypes,
-        fitnesses=fitnesses,
-        descriptors=descriptors,
-        extra_scores=extra_scores,
-    )
-```
-
-
 ## Contributing
 Issues and contributions are welcome. Please refer to the [contribution guide](https://qdax.readthedocs.io/en/latest/guides/CONTRIBUTING/) in the documentation for more details.
 

docs/api_documentation/core/cma_mega.md

@@ -0,0 +1,5 @@
+# Covariance Matrix Adaptation MAP-Elites via Gradient Arborescence (CMA-MEGA)
+
+To create an instance of CMA-MEGA, one need to use an instance of [MAP-Elites](map_elites.md) with the CMAMEGAEmitter, detailed below.
+
+::: qdax.core.emitters.cma_mega_emitter.CMAMEGAEmitter

docs/api_documentation/core/dads.md

@@ -1,3 +1,3 @@
 # DADS class
 
-::: qdax.core.dads.DADS
+::: qdax.baselines.dads.DADS

docs/api_documentation/core/diayn.md

@@ -1,3 +1,3 @@
 # DIAYN class
 
-::: qdax.core.diayn.DIAYN
+::: qdax.baselines.diayn.DIAYN

docs/api_documentation/core/genetic_algorithm.md

@@ -1,3 +1,3 @@
 # Genetic Algorithm class
 
-::: qdax.core.genetic_algorithm.GeneticAlgorithm
+::: qdax.baselines.genetic_algorithm.GeneticAlgorithm

docs/api_documentation/core/map_elites.md

@@ -1,3 +1,7 @@
 # MAP Elites class
 
+This class implement the base mechanism of MAP-Elites. It must be used with an emitter. To get the usual MAP-Elites algorithm, one must use the [mixing emitter](emitters.md#qdax.core.emitters.standard_emitters.MixingEmitter).
+
+The MAP-Elites class can be used with other emitters to create variants, like [PGAME](pgame.md), [CMA-MEGA](cma_mega.md) and [OMG-MEGA](omg_mega.md).
+
 ::: qdax.core.map_elites.MAPElites

docs/api_documentation/core/nsga2.md

@@ -1,3 +1,3 @@
 # NSGA2 class
 
-::: qdax.core.nsga2.NSGA2
+::: qdax.baselines.nsga2.NSGA2

docs/api_documentation/core/omg_mega.md

@@ -0,0 +1,5 @@
+# Objective and Measure Gradient MAP-Elites via Gradient Arborescence (OMGMEGA)
+
+To create an instance of OMGMEGA, one need to use an instance of [MAP-Elites](map_elites.md) with the OMGMEGAEmitter, detailed below.
+
+::: qdax.core.emitters.omg_mega_emitter.OMGMEGAEmitter

docs/api_documentation/core/pgame.md

@@ -0,0 +1,5 @@
+# Policy Gradient Assisted MAP Elites (PGAME)
+
+To create an instance of PGAME, one need to use an instance of [MAP-Elites](map_elites.md) with the PGAMEEmitter, detailed below.
+
+::: qdax.core.emitters.pga_me_emitter.PGAMEEmitter

docs/api_documentation/core/sac.md

@@ -1,3 +1,3 @@
 # SAC class
 
-::: qdax.core.sac.SAC
+::: qdax.baselines.sac.SAC

docs/api_documentation/core/smerl.md

@@ -1,5 +1,5 @@
 # SMERL classes for DIAYN and DADS
 
-::: qdax.core.diayn_smerl.DIAYNSMERL
+::: qdax.baselines.diayn_smerl.DIAYNSMERL
 
-::: qdax.core.dads_smerl.DADSSMERL
+::: qdax.baselines.dads_smerl.DADSSMERL

docs/api_documentation/core/spea2.md

@@ -1,3 +1,3 @@
 # SPEA2 class
 
-::: qdax.core.spea2.SPEA2
+::: qdax.baselines.spea2.SPEA2

docs/api_documentation/core/td3.md

@@ -1,3 +1,3 @@
 # TD3 class
 
-::: qdax.core.td3.TD3
+::: qdax.baselines.td3.TD3

docs/css/mkdocstrings.css

@@ -0,0 +1,37 @@
+.field-list {
+    margin-left: 2% !important;
+    padding: 4% !important;
+    border-left-style: solid !important;
+    border-left-color: #2980B9 !important;
+}
+
+.doc-method {
+    margin-top: 5%;
+    padding-top: 5%;
+    border-top-style: solid !important;
+    border-top-color: #c9c9c9 !important;
+}
+
+.doc-children {
+    margin-left: 2% !important;
+}
+
+.doc-class,
+.doc-function {
+    margin-bottom: 10% !important;
+    padding-bottom: 5%;
+    border-bottom-style: solid !important;
+    border-bottom-color: #4e4a4a !important;
+}
+
+.doc-attribute {
+    margin-bottom: 5% !important;
+}
+
+details.quote {
+    margin-top: 2%;
+}
+
+.wy-nav-content {
+    max-width: 1000px !important;
+}