edit links to move to main branch + small docs

README.md

@@ -162,10 +162,13 @@ v0.6.1)
 - v1.0.3
     - Adds inference mode to Gym environment
     - Adds seed to Gym Environment
+    - Submission example folder containing a trained agent
+    - Provide submission details for the competition
+    - Documentation for training on AWS
 
 - v1.0.2
     - Adds custom resolution for docker training as well
-    - fix version checker
+    - Fix version checker
 
 - v1.0.0
     - Adds custom resolution to both Unity and Gym environments

documentation/README.md

@@ -6,6 +6,8 @@ You can find here the following documentation:
 - [How to design configuration files](configFile.md)
 - [How training works](training.md)
 - [All the objects you can include in the arenas as well as their specifications](definitionsOfObjects.md)
+- [How to submit your agent](submission.md)
+- [A guide to train on AWS](cloudTraining.md)
 
 
 More will come before the competition launches.

documentation/cloudTraining.md

@@ -56,7 +56,7 @@ For example, should you wish to train a standard Dopamine agent provided in `ani
 lines to your docker in the `YOUR COMMANDS GO HERE` part, below the line installing `animalai-train`:
 
 ```
-RUN git clone --single-branch --branch submission https://github.com/beyretb/AnimalAI-Olympics.git
+RUN git clone https://github.com/beyretb/AnimalAI-Olympics.git
 RUN pip uninstall --yes tensorflow
 RUN pip install tensorflow-gpu==1.12.2
 RUN apt-get install unzip wget

examples/submission/README.md

@@ -0,0 +1,6 @@
+# Submission example
+
+We provide here the code for creating a submission container, as well as a very basic agent trained on `1-Food` using `trainMLAgents.py`. The `agent.py` implements the 
+script you will need to submit, it loads a trained model located in `data`.
+
+Read the [submission documentation](../../documentation/submission.md)