Updated README.

README.txt

@@ -35,4 +35,32 @@ enduro
   * input space     [210, 160, 1]
   * action space    [9,]
 
-The implementation, examples and results are pr
+The implementation, examples and results are presented in their corresponding directories. During
+training of the latter four games, Orion HPC (https://orion.nmbu.no) at the Norwegian University of
+Life Sciences (NMBU) provided computational resources.
+
+---
+
+N.b., in order for the examples to access atari games from `gymnasium`, Python<=3.10 must be used.
+
+---
+
+Relevant papers:
+
+- "Human-level control through deep reinforcement learning"
+                                    doi:10.1038/nature14236
+- "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm"
+                                                                        arXiv:1712.01815v1
+
+---
+
+Learning goals:
+
+- Understand and know how to build, use and deploy reinforcement learning algorithms
+  * Experiment with reinforcement agent(s) (for instance playing video-games)
+
+Learning outcomes:
+
+- Be competent in modern deep learning situations
+  * Understand (and to some extent be able to reproduce) cutting-edge “artificial intelligence”
+    models