use dict string key

src/mcts.jl

@@ -120,14 +120,14 @@ end
 ```jldoctest
 julia> using Revise
 julia> using YiemAgent, DataStructures
-julia> initialState = Dict{Symbol, Any}(
-          :customerinfo=> Dict{Symbol, Any}(),
-          :storeinfo=> Dict{Symbol, Any}(),  
+julia> initialState = Dict{String, Any}(
+           "customerinfo"=> Dict{String, Any}(),
+           "storeinfo"=> Dict{String, Any}(),  
 
-          :thoughtHistory=> OrderedDict{Symbol, Any}(
-            :question=> "How are you?",
-            )  
-          )
+           "thoughtHistory"=> OrderedDict{String, Any}(
+             "question"=> "How are you?",
+             )  
+           )
 julia> statetype = typeof(initialState)
 julia> root = YiemAgent.MCTSNode(initialState, 0, 0.0, Dict{statetype, YiemAgent.MCTSNode}())
 julia> YiemAgent.isleaf(root)
@@ -247,7 +247,7 @@ function _expand(node::MCTSNode,transition::Function, transitionargs::NamedTuple
     """
     if newNodeKey ∉ keys(node.children)
       newNode = MCTSNode(newNodeKey, newstate, 0, progressvalue, 0, newstate[:reward], 
-          newstate[:isterminal], node, Dict{String, MCTSNode}(), Dict{Symbol, Any}())
+          newstate[:isterminal], node, Dict{String, MCTSNode}(), Dict{String, Any}())
       node.children[newNodeKey] = newNode
     end
 end
@@ -273,14 +273,14 @@ end
 # Return
   - `simTrajectoryReward::Number`
     Cumulative reward collected along the simulation trajectory
-  - `terminalstate::Union{Dict{Symbol, Any}, Nothing}`
+  - `terminalstate::Union{Dict{String, Any}, Nothing}`
     Final state if terminal state reached, nothing otherwise
 
 # Signature
 """
 function simulate(node::MCTSNode, transition::Function, transitionargs::NamedTuple; 
   maxSimulationDepth::Integer=3, horizontalSample::Integer=3, multithread=false
-  )::NamedTuple{(:simTrajectoryReward, :terminalstate), Tuple{<:Number, Union{Dict{Symbol, Any}, Nothing}}}
+  )::NamedTuple{(:simTrajectoryReward, :terminalstate), Tuple{<:Number, Union{Dict{String, Any}, Nothing}}}
 
   simTrajectoryReward = 0.0
   terminalstate = nothing
@@ -319,7 +319,7 @@ end
 #     Whether this state is terminal
 
 # # Return
-#   - `Tuple{String, Dict{Symbol, <:Any}}`
+#   - `Tuple{String, Dict{String, <:Any}}`
 #     A tuple containing:
 #     - A unique node key string
 #     - A new state dictionary with updated thought history and metadata
@@ -333,7 +333,7 @@ end
 # """
 # function makeNewState(currentstate::T1, thoughtDict::T4, response::T2, select::Union{T3, Nothing}, 
 #   reward::T3, isterminal::Bool
-#   )::Tuple{String, Dict{Symbol, <:Any}} where {T1<:AbstractDict, T2<:AbstractString, T3<:Number, T4<:AbstractDict}
+#   )::Tuple{String, Dict{String, <:Any}} where {T1<:AbstractDict, T2<:AbstractString, T3<:Number, T4<:AbstractDict}
 
 #   # Find the latest thought key and index from current state's thought history
 #   currentstate_latestThoughtKey, currentstate_latestThoughtIndice =