update

src/interface.jl

@@ -439,7 +439,7 @@ function conversation(a::T, userinput::Dict) where {T<:agent}
           )  
         )
       bestplan = runMCTS(a, initialState, decisionMaker, progressValueEstimator, reflector,
-                        isterminal, 2, 3, 100, 1.0)
+                        isterminal, 2, 3, 2, 1.0)
       error("---> bestplan")
 
       # actor loop(bestplan)

src/mcts.jl

@@ -163,7 +163,7 @@ julia>
 
 # TODO
   - [] update docstring
-  - [WORKING] implement the function
+  - [x] implement the function
   - [] check for the terminal state (node.reward != 0), break if it is terminal state
 
 # Signature
@@ -185,24 +185,6 @@ function simulate(a, node::MCTSNode, decisionMaker::Function, progressValueEstim
 
   return simTrajectoryReward
 end
-# function simulate(a, node::MCTSNode, decisionMaker::Function, progressValueEstimator::Function, 
-#   isterminal::Function, max_depth::Int; n=3)::Number
-
-#   simTrajectoryReward = 0.0
-  
-#   for _ in 1:max_depth
-#     node = selectChildNode(node)
-#     simTrajectoryReward += node.reward
-
-#     if node.isterminal
-#       break
-#     else
-#       expand(a, node, decisionMaker, progressValueEstimator, isterminal, n=n)
-#     end
-#   end
-
-#   return simTrajectoryReward
-# end
 
 """