diff --git a/DecMCTS.py b/DecMCTS.py index 24c334ca5910ff0be9c47c8bbe43bfc6afc8fa15..d51b2235a9974e0f48247c413d1f5a830b3da662 100644 --- a/DecMCTS.py +++ b/DecMCTS.py @@ -189,7 +189,7 @@ class Tree: """ state = self._get_state(start_node) - options = self.available_actions(self.data, state) + options = self.available_actions(self.data, state, self.id) # create empty nodes underneath the node being expanded for o in options: diff --git a/README.md b/README.md index 3110b47e48301a6ef743ae0bc0edfecb6a04e953..07b02ea5d46a07b6f19228df8bd91b759c8289a2 100644 --- a/README.md +++ b/README.md @@ -21,8 +21,8 @@ data = {} # Create an available actions function # This returns a list of possible actions to take from a given state -# state input explained next -def avail_actions(data, state): +# state and robot_id inputs explained below +def avail_actions(data, state, robot_id): # This example is simply getting max sum, # options are same regardless of state diff --git a/test/test.py b/test/test.py index 9255c0b03275851c6c312e7192a80106429ec0d5..80204aa2536d11406f33c0d9160cf7d6613c7799 100644 --- a/test/test.py +++ b/test/test.py @@ -3,7 +3,7 @@ from DecMCTS import Tree data = {} -def avail_actions(data, state): +def avail_actions(data, state, robot_id): return [1,2,3,4,5] def reward(dat, state):