ton/YiemAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
narawat lamaiin
2024-05-06 20:42:11 +07:00
parent 4608835c95
commit 99ec9a4960
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/mcts.jl
View File

@@ -182,6 +182,7 @@ function simulate(a, node::MCTSNode, decisionMaker::Function, progressValueEstim
for depth in 1:maxDepth for depth in 1:maxDepth
if node.isterminal if node.isterminal
simTrajectoryReward += node.reward
break break
else else
simTrajectoryReward += node.reward simTrajectoryReward += node.reward
@@ -448,12 +449,15 @@ function runMCTS(
while !isleaf(node) while !isleaf(node)
node = UCTselect(node, w) node = UCTselect(node, w)
end end
if node.isterminal
expand(a, node, decisionMaker, progressValueEstimator, isterminal, n=n) # MCTS arrive at the leaf node that is also a terminal state,
# do nothing then go directly to backpropagation
leafNode = UCTselect(node, w) else
simTrajectoryReward = simulate(a, leafNode, decisionMaker, progressValueEstimator, expand(a, node, decisionMaker, progressValueEstimator, isterminal, n=n)
isterminal, maxDepth, n=n) leafNode = UCTselect(node, w)
simTrajectoryReward = simulate(a, leafNode, decisionMaker, progressValueEstimator,
isterminal, maxDepth, n=n)
end
backpropagate(leafNode, simTrajectoryReward) backpropagate(leafNode, simTrajectoryReward)
end end