Learning Planning Heuristics through Observation
نویسندگان
چکیده
Michael Dyer Artificial Intelligence Lab Computer Science Department UCLA Abst rac t This paper diacusses a method for learning thematic level structures, i.e. abstract plan/goal combinations, by observing the bad planning behavior of narrative characters. The learning method discussed is a one-trial, schema acquisition method, which is similar to DeJong's [DeJong, 1983]. The method uses constraint-based causal reasoning to construct a new schema which characterizes a situation. This work is part of the MORRIS project at UCLA [Dyer, 1983b].
منابع مشابه
Learning to Rank for Synthesizing Planning Heuristics
We investigate learning heuristics for domainspecific planning. Prior work framed learning a heuristic as an ordinary regression problem. However, in a greedy best-first search, the ordering of states induced by a heuristic is more indicative of the resulting planner’s performance than mean squared error. Thus, we instead frame learning a heuristic as a learning to rank problem which we solve u...
متن کاملThe Nature of Heuristics II : Background and Examples
Machine learning can be categorized along many dimensions, an important one of which is `degree o f human guidance or forethought' . This continuum stretches from rote learning, through carefully guided concept-formation by observation, out toward independent theory formation . Six years ago, the AM program was constructed as an experiment in this latter kind of learning by discovery . Its sour...
متن کاملPlanning Graph Heuristics for Scaling Up Conformant Planning
This paper describes a set of heuristics for efficiently solving conformant planning problems. Conformant planning, as described in this paper extends classical planning to problems where there is uncertainty in the initial state. The motivation for improved heuristic techniques stems from the observation that previous conformant planners used largely uninformed heuristics. We show that the rea...
متن کاملTransfer of Learned Heuristics among Planners∗
This paper presents a study on the transfer of learned control knowledge between two different planning techniques. We automatically learn heuristics (usually, in planning, heuristics are also named control knowledge) from one planner search process and apply them to a different planner. The goal is to improve this second planner efficiency solving new problems, i.e. to reduce computer resource...
متن کاملToward Discriminative Learning of Planning Heuristics
We consider the problem of learning heuristics for controlling forward state-space search in AI planning domain. We draw on a recent framework for “structured output classification” (e.g. syntactic parsing) known as learning as search optimization (LaSO). The LaSO approach uses discriminative learning to optimize heuristic functions for search-based computation of structured outputs and has sho...
متن کامل