updated

Author: arunp77

reinforcement_learning.html

@@ -172,15 +172,15 @@ <h2>Introduction</h2>
         <div class="section" id="core-idea">
         <h2>Core Components of Reinforcement Learning:</h2>
             <ul>
-                <li><strong>Agent:</strong> The learner or decision-maker.</li>
-                <li><strong>Environment:</strong> Everything the agent interacts with.</li>
-                <li><strong>State (S):</strong> A representation of the current situation.</li>
-                <li><strong>Action (A):</strong> All possible moves the agent can take.</li>
-                <li><strong>Reward (R):</strong> A scalar feedback signal; guides the agent.</li>
-                <li><strong>Policy (π):</strong> Strategy used by the agent to decide actions.</li>
-                <li><strong>Value Function (V):</strong> Predicts future rewards.</li>
-                <li><strong>Q-Function (Q):</strong> Predicts future rewards for action-state pairs.</li>
-                <li><strong>Model (optional):</strong> Predicts the next state and reward.</li>
+                <li><strong>Agent: </strong> The learner or decision-maker.</li>
+                <li><strong>Environment: </strong> Everything the agent interacts with.</li>
+                <li><strong>State (S): </strong> A representation of the current situation.</li>
+                <li><strong>Action (A): </strong> All possible moves the agent can take.</li>
+                <li><strong>Reward (R): </strong> A scalar feedback signal; guides the agent.</li>
+                <li><strong>Policy (π): </strong> Strategy used by the agent to decide actions.</li>
+                <li><strong>Value Function (V): </strong> Predicts future rewards.</li>
+                <li><strong>Q-Function (Q): </strong> Predicts future rewards for action-state pairs.</li>
+                <li><strong>Model (optional): </strong> Predicts the next state and reward.</li>
             </ul>
         <h3>Types of Reinforcement Learning</h3>
             <ol>