update

2025-03-18 21:23:09 +07:00
parent 693cbfd82d
commit ee5f8a8a52
2 changed files with 92 additions and 84 deletions
@@ -1,7 +1,7 @@
 module mcts
  
 export selectBestNextNode, selectBestTrajectoryNode, backpropagate, isleaf, isroot, selectChildNode,
-        expand, simulate, makeNewState
+        expand, simulate
 using Base.Threads
 using GeneralUtils

@@ -302,84 +302,84 @@ function simulate(node::MCTSNode, transition::Function, transitionargs::NamedTup
          terminalstate=terminalstate)
 end

-""" Make new state
+# """ Make new state

-# Arguments
-  - `currentstate::T1`
-    Current state dictionary containing thought history and metadata
-  - `thoughtDict::T4`
-    Dictionary containing new thought and action
-  - `response::T2`
-    Response string from the environment
-  - `select::Union{T3, Nothing}`
-    Selection value or nothing
-  - `reward::T3`
-    Reward value for this state
-  - `isterminal::Bool`
-    Whether this state is terminal
+# # Arguments
+#   - `currentstate::T1`
+#     Current state dictionary containing thought history and metadata
+#   - `thoughtDict::T4`
+#     Dictionary containing new thought and action
+#   - `response::T2`
+#     Response string from the environment
+#   - `select::Union{T3, Nothing}`
+#     Selection value or nothing
+#   - `reward::T3`
+#     Reward value for this state
+#   - `isterminal::Bool`
+#     Whether this state is terminal

-# Return
-  - `Tuple{String, Dict{Symbol, <:Any}}`
-    A tuple containing:
-    - A unique node key string
-    - A new state dictionary with updated thought history and metadata
+# # Return
+#   - `Tuple{String, Dict{Symbol, <:Any}}`
+#     A tuple containing:
+#     - A unique node key string
+#     - A new state dictionary with updated thought history and metadata

-# Example
-```jldoctest
-julia> 
-```
+# # Example
+# ```jldoctest
+# julia> 
+# ```

-# Signature
-"""
-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}
+# # Signature
+# """
+# 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}

-  # Find the latest thought key and index from current state's thought history
-  currentstate_latestThoughtKey, currentstate_latestThoughtIndice = 
-      GeneralUtils.findHighestIndexKey(currentstate[:thoughtHistory], "thought")
-  # Calculate next index for new thought/action
-  currentstate_nextIndice = 
-              currentstate_latestThoughtKey == :NA ? 1 : currentstate_latestThoughtIndice + 1
-  # Create new keys for thought and action based on next index
-  currentstate_latestThoughtKey = Symbol("thought_$currentstate_nextIndice")
-  latestActionKey = Symbol("action_$currentstate_nextIndice")
+#   # Find the latest thought key and index from current state's thought history
+#   currentstate_latestThoughtKey, currentstate_latestThoughtIndice = 
+#       GeneralUtils.findHighestIndexKey(currentstate[:thoughtHistory], "thought")
+#   # Calculate next index for new thought/action
+#   currentstate_nextIndice = 
+#               currentstate_latestThoughtKey == :NA ? 1 : currentstate_latestThoughtIndice + 1
+#   # Create new keys for thought and action based on next index
+#   currentstate_latestThoughtKey = Symbol("thought_$currentstate_nextIndice")
+#   latestActionKey = Symbol("action_$currentstate_nextIndice")

-  # Find the latest thought index from input thought dictionary
-  _, thoughtDict_latestThoughtIndice = 
-      GeneralUtils.findHighestIndexKey(thoughtDict, "thought")
+#   # Find the latest thought index from input thought dictionary
+#   _, thoughtDict_latestThoughtIndice = 
+#       GeneralUtils.findHighestIndexKey(thoughtDict, "thought")
  
-  # Determine thought and action keys from thought dictionary
-  thoughtDict_latestThoughtKey, thoughtDict_latestActionKey =
-  if thoughtDict_latestThoughtIndice == -1
-    (:thought, :action)
-  else
-    (
-      Symbol("thought_$thoughtDict_latestThoughtIndice"), 
-      Symbol("action_$thoughtDict_latestThoughtIndice"),
-    )
-  end
+#   # Determine thought and action keys from thought dictionary
+#   thoughtDict_latestThoughtKey, thoughtDict_latestActionKey =
+#   if thoughtDict_latestThoughtIndice == -1
+#     (:thought, :action)
+#   else
+#     (
+#       Symbol("thought_$thoughtDict_latestThoughtIndice"), 
+#       Symbol("action_$thoughtDict_latestThoughtIndice"),
+#     )
+#   end

-  # Create new state by deep copying current state
-  newstate = deepcopy(currentstate)
-  # Update thought history with new thought
-  newstate[:thoughtHistory][currentstate_latestThoughtKey] = 
-      thoughtDict[thoughtDict_latestThoughtKey]
-  # Update thought history with new action
-  newstate[:thoughtHistory][latestActionKey] = thoughtDict[thoughtDict_latestActionKey]
-  # Create and add new observation to thought history
-  newObservationKey = Symbol("observation_$(currentstate_nextIndice)")
-  newstate[:thoughtHistory][newObservationKey] = response
-  # Update state metadata
-  newstate[:reward] = reward
-  newstate[:select] = select
-  newstate[:isterminal] = isterminal
+#   # Create new state by deep copying current state
+#   newstate = deepcopy(currentstate)
+#   # Update thought history with new thought
+#   newstate[:thoughtHistory][currentstate_latestThoughtKey] = 
+#       thoughtDict[thoughtDict_latestThoughtKey]
+#   # Update thought history with new action
+#   newstate[:thoughtHistory][latestActionKey] = thoughtDict[thoughtDict_latestActionKey]
+#   # Create and add new observation to thought history
+#   newObservationKey = Symbol("observation_$(currentstate_nextIndice)")
+#   newstate[:thoughtHistory][newObservationKey] = response
+#   # Update state metadata
+#   newstate[:reward] = reward
+#   newstate[:select] = select
+#   newstate[:isterminal] = isterminal

-  # Generate unique ID for new node
-  newNodeKey = GeneralUtils.uuid4snakecase()
+#   # Generate unique ID for new node
+#   newNodeKey = GeneralUtils.uuid4snakecase()

-  return (newNodeKey, newstate)
-end
+#   return (newNodeKey, newstate)
+# end