update README.md

simerplaha · May 9, 2020 · 711fbfb · 711fbfb
1 parent 81ebb1f
commit 711fbfb
Show file tree

Hide file tree

Showing 6 changed files with 7 additions and 7 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 # Reinforcement learning
 
-Material referred
+Referred material
 
 - Book by Sutton & Barto - [Reinforcement Learning: An Introduction](http://incompleteideas.net/book/the-book-2nd.html)
 - Lectures by David Silver - [Introduction to reinforcement learning](https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ) 
@@ -20,7 +20,7 @@ Last lever has the highest probability (`0.90`) therefore has more chance of get
 
 ## Student Markov Chain
 
-Implements the `Student MDP` at David Silver's lecture 2 at [this (24:56)](https://youtu.be/lfHX2hHRMVQ?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ&t=1496) timestamp.
+Implements the `Student MDP` from David Silver's lecture 2 at [this (24:56)](https://youtu.be/lfHX2hHRMVQ?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ&t=1496) timestamp.
 There are tests in [StudentSpec](/src/test/scala/lecture/StudentSpec.scala) that prove that no other state can 
 return the same optimal value as optimal state using bellman's equation.  
 
@@ -38,7 +38,7 @@ Implements bellman's equation to find the quickest path to targets within a grid
 The following shows results of a 11x11 grid with 3 goal targets - ⌂ (circled green). The arrows indicate the optimal direction 
 to take at each grid to reach the nearest target.  
 
-![direction](doc/img/grid_direction_green.png "direction")
+![direction](doc/img/grid_direction.png "direction")
 
 Value function created after 100 value iteration.
 

diff --git a/doc/img/grid_direction.png b/doc/img/grid_direction.png
diff --git a/doc/img/grid_direction_green.png b/doc/img/grid_direction_green.png
diff --git a/doc/img/grid_values.png b/doc/img/grid_values.png
diff --git a/src/main/scala/grid/GridWorld.scala b/src/main/scala/grid/GridWorld.scala
@@ -12,7 +12,7 @@ object GridWorld extends App {
    * Default terminals are top left, middle and bottom right.
    */
   val terminals: Seq[(Int, Int)] =
-    Seq((0, 0), ((gridRows - 1) / 2, (gridCols - 1) / 2), (gridRows - 1, gridCols - 1))
+    Seq((0, 0), (gridRows - 1, gridCols - 1))
 
   sealed trait Grid
   object Grid {

diff --git a/src/main/scala/tictactoe/Game.scala b/src/main/scala/tictactoe/Game.scala
@@ -36,9 +36,9 @@ object Game {
 
     println(
       """
-        |************
-        |Game started
-        |************
+        |*********************************************
+        |Game started - TODO - needs better prediction
+        |*********************************************
         |""".stripMargin)
 
     println("You are X and the bot is O")