update

README.md

@@ -13,7 +13,7 @@ MCTS is a powerful search algorithm that balances exploration and exploitation t
 However, in many real-world problems, **rewards are sparse**—they only come at the final state. This creates two critical problems:
 
 1. **Value estimation delay** — Rewards must propagate backward through many layers before affecting early decisions
-2. **Exploration inefficiency** — Without intermediate signals, MCTS explores randomly until it偶然 discovers a reward
+2. **Exploration inefficiency** — Without intermediate signals, MCTS explores randomly until it discovers a reward
 
 ### How LLMs Fix the Sparse Reward Problem
 
@@ -138,13 +138,13 @@ function transition(state::Dict, args::NamedTuple)
 end
 
 # Define transition arguments
-transition_args = (param1 = "value1", param2 = "value2")
+transitionargs = (param1 = "value1", param2 = "value2")
 
 # Run MCTS
 result = runMCTS(
     initialstate,
     transition,
-    transition_args;
+    transitionargs;
     maxiterations = 10,
     explorationweight = 1.0,
     maxSimulationDepth = 3
@@ -162,9 +162,9 @@ high_value_states = result.highValueStateList
 ```julia
 # With custom parameters
 result = runMCTS(
-    initialState,
+    initialstate,
     transition_func,
-    transition_args;
+    transitionargs;
     horizontalSampleExpansionPhase = 5,      # More children during expansion
     horizontalSampleSimulationPhase = 3,     # Sample 3 children during simulation
     maxSimulationDepth = 5,                  # Deeper search
@@ -203,12 +203,19 @@ Search for the best action to take for a given state and task.
 
 #### `simulateThenBackpropagate(node, transition, transitionargs; kwargs...)`
 
-Run simulation from a node and backpropagate the reward.
+Run simulation from a node and backpropagate the reward. Returns `nothing`.
+
+**Keyword Arguments:**
+- `maxSimulationDepth::Integer=3` — Maximum simulation depth
+- `horizontalSampleSimulationPhase::Integer=3` — Children per simulation node
+- `saveSimulatedNode::Bool=false` — Keep simulation nodes
+- `multithread::Bool=false` — Enable multithreading
+- `highValueState` — Channel to store high-value states
 
 ### Utility Functions
 
 - `UCTselect(node, w)` — Select node using UCT score
-- `dictify(x; keytype=Any, stringkey=false)` — Convert JSON.Object/OrderedDict to plain Dict
+- `dictify(x; keytype=Any)` — Convert JSON.Object/OrderedDict to plain Dict
 
 ### MCTS Node Structure
 
@@ -255,7 +262,7 @@ Where:
 | Scenario | Alternative approach |
 |----------|---------------------|
 | **Dense rewards available** | Use pure RL with reward shaping |
-| **Simple决策 problems** | Classical search (DFS, BFS) is sufficient |
+| **Simple decision problems** | Classical search (DFS, BFS) is sufficient |
 | **Real-time constraints** | LLM calls may be too slow; use pre-trained value function |
 | **No LLM access** | Use pure MCTS with hand-designed heuristics |