Plan-graph Based Heuristics for Conformant Probabilistic Planning
نویسندگان
چکیده
In this paper, we introduce plan-graph based heuristics to solve a variation of the conformant probabilistic planning (CPP) problem. In many real-world problems, it is the case that the sensors are unreliable or take too many resources to provide knowledge about the environment. These domains are better modeled as conformant planning problems. POMDP based techniques are currently the most successful approach for solving CPP but have the limitation of statespace explosion. Recent advances in deterministic and conformant planning have shown that plan-graphs can be used to enhance the performance significantly. We show that this enhancement can also be translated to CPP. We describe our process for developing the plan-graph heuristics and estimating the probability of a partial plan. We compare the performance of our planner PVHPOP when used with diffrent heuristics. We also perform a comparison with a POMDP solver to show over a order of magnitude improvement in performance.
منابع مشابه
Probapop: Probabilistic Partial-Order Planning
We describe Probapop, a partial-order probabilistic planning system. Probapop is a blind (conformant) planner that finds plans for domains involving probabilistic actions but no observability. The Probapop implementation is based on Vhpop, a partial-order deterministic planner written in C++. The Probapop algorithm uses plan graph based heuristics for selecting a plan from the search queue, and...
متن کاملSequential Monte Carlo in Probabilistic Planning Reachability Heuristics
The current best conformant probabilistic planners encode the problem as a bounded length CSP or SAT problem. While these approaches can find optimal solutions for given plan lengths, they often do not scale for large problems or plan lengths. As has been shown in classical planning, heuristic search outperforms CSP/SAT techniques (especially when a plan length is not given a priori). The probl...
متن کاملSequential Monte Carlo in reachability heuristics for probabilistic planning
Some of the current best conformant probabilistic planners focus on finding a fixed length plan with maximal probability. While these approaches can find optimal solutions, they often do not scale for large problems or plan lengths. As has been shown in classical planning, heuristic search outperforms bounded length search (especially when an appropriate plan length is not given a priori). The ...
متن کاملSequential Monte Carlo in Probabilistic Planning Reachability Heuristics
The current best conformant probabilistic planners encode the problem as a bounded length CSP or SAT problem. While these approaches can find optimal solutions for given plan lengths, they often do not scale for large problems or plan lengths. As has been shown in classical planning, heuristic search outperforms CSP/SAT techniques (especially when a plan length is not given a priori). The probl...
متن کاملApplying Search Based Probabilistic Inference Algorithms to Probabilistic Conformant Planning: Preliminary Results
Probabilistic conformant planning problems can be solved by probabilistic inference algorithms after translating their PPDDL specifications into graphical models. We present two translation schemes that convert probabilistic conformant planning problems as graphical models. The first encoding is based on the probabilistic extension of the serial encoding of PDDL in SatPlan, and the second encod...
متن کامل