diff --git a/src/mcts.jl b/src/mcts.jl index 7d30568..0c6e3f3 100644 --- a/src/mcts.jl +++ b/src/mcts.jl @@ -175,45 +175,6 @@ function expand(a::T1, node::MCTSNode, decisionMaker::Function, end end end -# function expand(a::T1, node::MCTSNode, decisionMaker::Function, -# progressValueEstimator::Function, reflector::Function; n::Integer=3) where {T1<:agent} - -# nthSample = 0 -# while nthSample <= n -# nthSample += 1 -# println("---> expand() sample $nthSample") -# thoughtDict = decisionMaker(a, node.state) - -# newNodeKey, newstate, reward, isterminalstate = -# MCTStransition(a, node.state, thoughtDict) - -# # add progressValueEstimator -# stateevaluation, statevalue = progressValueEstimator(a, newstate) - -# if reward < 0 -# pprint(newstate[:thoughtHistory]) -# newstate[:evaluation] = stateevaluation -# newstate[:lesson] = reflector(a, newstate) - -# # store new lesson for later use -# lessonDict = copy(JSON3.read("lesson.json")) -# latestLessonKey, latestLessonIndice = -# GeneralUtils.findHighestIndexKey(state[:thoughtHistory], "lesson") -# nextIndice = latestLessonKey == :NA ? 1 : latestLessonIndice + 1 -# newLessonKey = Symbol("lesson_$(nextIndice)") -# lessonDict[newLessonKey] = newstate -# open("lesson.json", "w") do io -# JSON3.pretty(io, lessonDict) -# end -# print("---> reflector()") -# end - -# if newNodeKey ∉ keys(node.children) -# node.children[newNodeKey] = MCTSNode(newNodeKey, newstate, 0, statevalue, -# reward, isterminalstate, node, Dict{String, MCTSNode}()) -# end -# end -# end