add Project 2 Report

Author: Mohammedabdalqader

Project-2_Continuous-Control/Report.md

@@ -0,0 +1,13 @@
+# Continuous Control
+
+While working on this project, I had to invest too much time in research to find the right algorithms for such a problem. There were many options available to me, and this was a challenge for me, and from here my journey began.
+
+There is really a very useful repo that describes and implements different algorithms that work very well for such a problem with continuous action space. Thanks to this repo and other sources, I was able to understand some algorithms correctly, including the DDPG, D4PG, PPO, A2C, and A3C algorithms, and I was able to implement some of these algorithms to solve my problem.
+
+In this report I will explain everything about this project in details. So we will look at different aspects like:
+- **Actor-Critic**
+- **Distributed distributional deep deterministic policy gradients (D4PG) algorithm**
+- **Model architectures**
+- **Hayperparameters**
+- **Future Work**
+