#54 Update doc strings

Author: pockerman

README.md

@@ -56,7 +56,7 @@ The images below show the overall running distortion average and running reward
 
 The following packages are required. 
 
-- NumPy
+- <a href="#">NumPy</a>
 - <a href="https://www.sphinx-doc.org/en/master/">Sphinx</a> 
 - <a href="#">Python Pandas</a>
 

requirements.txt

@@ -2,3 +2,4 @@ numpy==1.20.2
 pandas==1.1.3
 gym==0.18.0
 textdistance==4.2.0
+numpydoc==1.2

src/algorithms/q_learning.py

@@ -14,9 +14,7 @@
 
 
 class QLearnConfig(object):
-    """
-    Configuration  for Q-learning
-    """
+    """Configuration  for Q-learning"""
     def __init__(self):
         self.gamma: float = 1.0
         self.alpha: float = 0.1
@@ -25,11 +23,13 @@ def __init__(self):
 
 
 class QLearning(WithMaxActionMixin):
-    """
-    Q-learning algorithm implementation
-    """
+    """Q-learning algorithm implementation"""
 
     def __init__(self, algo_config: QLearnConfig):
+        """
+        Constructor. Constructs an untrained agent
+        :param algo_config: Configuration parameters
+        """
         super(QLearning, self).__init__()
         self.q_table = {}
         self.config = algo_config