• Corpus ID: 34125893

Purely Declarative Action Representations are Overrated : Classical Planning with Simulators

  title={Purely Declarative Action Representations are Overrated : Classical Planning with Simulators},
  author={Guillem Franc{\`e}s and Miquel Ram{\'i}rez and Nir Lipovetzky and Hector Geffner},
Classical planning is concerned with problems where a goal needs to be reached from a known initial state by doing actions with deterministic, known effects. Classical planners, however, deal only with classical problems that can be expressed in declarative planning languages such as STRIPS or PDDL. This prevents their use on problems that are not easy to model declaratively or whose dynamics are given via simulations. Simulators do not provide a declarative representation of actions, but… 

Figures and Tables from this paper

Lifted Successor Generation Using Query Optimization Techniques

This work tackles the successor generation task, a key operation in forward-search planning, directly on the lifted representation using well-known techniques from database theory and shows how computing the variable substitutions that make an action schema applicable in a given state is essentially a query evaluation problem.

Action Selection for Transparent Planning

A novel framework to formalize and solve transparent planning tasks by executing actions selected in a suitable and timely fashion by proposing an action selection strategy via on-line planning that seeks actions to quickly convey the goal being pursued to an observer assumed to fit a given stereotype.

Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS

This work proposes Double-Stage Action Model Acquisition (DSAMA), a system that obtains a descriptive PDDL action model with explicit preconditions and effects over the propositional variables unsupervized-learned from images and argues that this translator bottleneck cannot be addressed just by using a different, existing rule-based learning method.

General Policies, Serializations, and Planning Width

It is shown that bounded width is a property of planning domains that admit optimal general policies in terms of features that are explicitly or implicitly represented in the domain encoding, and is extended to much larger class of domains with bounded serialized width where the general policies do not have to be optimal.

General Policies, Representations, and Planning Width

It is shown that bounded width is a property of planning domains that admit optimal general policies in terms of features that are explicitly or implicitly represented in the domain encoding, and this leads to a new simple, meaningful, and expressive language for specifying domain serializations in the form of policy sketches.

Classical Planning in Deep Latent Space

The proposed Latplan, an unsupervised architecture combining deep learning and classical planning, is evaluated using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.

Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches: Extended Version

Policy sketches are shown to be a powerful language for expressing domain-specific knowledge in a simple and compact way and a convenient alternative to languages such as HTNs or temporal logics, and make it easy to express general problem decompositions and prove key properties of them like their width and complexity.

A review of generalized planning

The paper reviews recent advances in generalized planning and relates them to existing planning formalisms, such as planning with domain control knowledge and approaches for planning under uncertainty, that also aim at generality.

Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary

This paper proposes LatPlan, an unsupervised architecture combining deep learning and classical planning, and develops Action Autoencoder / Discriminator, a neural architecture which jointly finds the action symbols and the implicit action models (preconditions/effects), and provides a successor function for the implicit graph search.

Best-First Width Search for Lifted Classical Planning

This work adapts best-first width search to the lifted setting and shows that this yields state-of-the-art performance for hard-to-ground planning tasks.



Structure and inference in classical planning

It is shown that many of the standard benchmark domains can be solved with almost no search or a polynomially bounded amount of search, once the structure of planning problems is taken into account.

A Concise Introduction to Models and Methods for Automated Planning

The goal is to provide a modern and coherent view of planning that is precise, concise, and mostly self-contained, without being shallow.

Classical Planning with Simulators: Results on the Atari Video Games

The empirical results over 54 Atari games show that the simplest such algorithm performs at the level of UCT, the state-of-the-art planning method in this domain, and suggest the potential of width-based methods for planning with simulators when factored, compact action models are not available.

GPT: A Tool for Planning with Uncertainty and Partial Information

GPT (General Planning Tool) is an integrated software tool for modeling, analyzing and solving a wide range of planning problems dealing with uncertainty and partial information, that has been used for us and others for research and teaching.

Modeling and Computation in Planning: Better Heuristics from More Expressive Languages

This work shows that the direct generalization of relaxed planning graph heuristics to more expressive languages that implicitly allow conjunctions of atoms with more than one state variable leaves open a crisp gap, as it fails to properly account for the constraints over these variables.

The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks

It is found that using landmarks improves performance, whereas the incorporation of action costs into the heuristic estimators proves not to be beneficial, and in some domains a search that ignores cost solves far more problems, raising the question of how to deal with action costs more effectively in the future.

Mercury Planner : Pushing the Limits of Partial Delete Relaxation

This work designs techniques aimed at making red-black plans executable, short-cutting the search, and is entered into sequential satisficing and agile tracks of the competition.

Blind Search for Atari-Like Online Planning Revisited

The planning effectiveness can be further improved by considering online planning for the Atari games as a multiarmed bandit style competition between the various actions available at the state planned for, and not purely as a classical planning style action sequence optimization problem.

The FF Planning System: Fast Plan Generation Through Heuristic Search

A novel search strategy is introduced that combines hill-climbing with systematic search, and it is shown how other powerful heuristic information can be extracted and used to prune the search space.