[Docs] add images

Author: fedebotu

docs/_content/api/models/base.md

@@ -1,5 +1,10 @@
 # Base Autoregressive Model
 
+
+<img class="full-img" alt="policy" src="https://user-images.githubusercontent.com/48984123/281976545-ca88f159-d0b3-459e-8fd9-89799be9d1b0.png">
+
+
+
 ## Policy
 
 ```{eval-rst}

docs/_content/api/models/env_embeddings.md

@@ -1,5 +1,16 @@
 # Environment Embeddings
 
+In autoregressive policies, environment embeddings transfer data from feature space to hidden space:
+
+- Initial Embeddings: encode global problem features
+- Context Embeddings: modify current node embedding during decoding
+- Dynamic Embeddings: modify all nodes embeddings during decoding
+
+<img class="full-img" alt="policy" src="https://user-images.githubusercontent.com/48984123/281976545-ca88f159-d0b3-459e-8fd9-89799be9d1b0.png">
+
+
+
+
 ## Context Embeddings
 
 The context embedding is used to modify the query embedding of the problem node of the current partial solution. Usually consists of a projection of gathered node embeddings and features to the embedding space.

docs/_content/api/models/zoo.md

@@ -34,11 +34,6 @@ Models from the literature and contributions are contained in the Model Zoo.
    :undoc-members:
 ```
 
-```{eval-rst}
-.. automodule:: rl4co.models.zoo.ppo.decoder
-   :members:
-   :undoc-members:
-```
 
 ## Heterogeneous Attention Model (HAM)
 
@@ -134,11 +129,6 @@ Models from the literature and contributions are contained in the Model Zoo.
    :undoc-members:
 ```
 
-```{eval-rst}
-.. automodule:: rl4co.models.zoo.pomo.decoder
-   :members:
-   :undoc-members:
-```
 
 ## Pointer Network (PtrNet)