This is a dynamic deterministic planner policy, which means if the source deterministic planner has not already computed and cached the plan for a query state, then this policy will first compute a plan using the planner and then return the answer
This class extends the OOMDPlanner to provide the interface and common mechanisms for classic deterministic forward search planners.
Creates a terminal function that indicates terminal states are any states that satisfy a goal condition where the goal condition is specified by a
This is a helper class that is used to run a planner from multiple initial states to ensure that an adequate plan/policy exists for each them.
This is a static deterministic planner policy, which means if the source deterministic planner has not already computed and cached the plan for a query state, then this policy is undefined for that state and will cause the policy to throw a corresponding
The SearchNode class is used for classic deterministic forward search planners.
A simple StateConditionTest wrapper of TerminalFunciton.
This Reward function returns a uniform cost (-1) for all transitions that do not transition to a goal state and 0 on transitions to the goal state.