update

src/mcts.jl

@@ -220,9 +220,9 @@ end
 
 # Arguments
   - `node::MCTSNode`
-    node of a search tree
+    leaf node of a search tree
   - `simTrajectoryReward::T`
-    total reward from all node in simulation trajectory
+    total reward from trajectory simulation
   
 # Return
   - `No return`
@@ -236,6 +236,9 @@ julia>
 """
 function backpropagate(node::MCTSNode, simTrajectoryReward::T;
                       discountRewardCoeff::AbstractFloat=0.9) where {T<:Number}
+  # [WORKING] store best trajectory 
+  isLeafNodeTerminalState = true 
+  terminalStateReward = node.reward
   while !isroot(node)
     # Update the statistics of the current node based on the result of the playout
     node.visits += 1