Connecting PDDL-based off-the-shelf planners to an arcade game
نویسندگان
چکیده
First, we explain the Iceblox game, which has its origin in the Pengo game. After carefully listing requirements on game playing, the contents of plans, their execution and planning problem generation, we design a set of benchmarks to select good playing candidates among currently available planners. We eventually selected two planners which are able to play the Iceblox video game well and mostly in real time. We outline our planning architecture and describe both the predicates and a couple of the operators we designed. We wish to report that we never tweaked the planners neither during the benchmarks nor during video game playing.
منابع مشابه
A PDDL-Based Planning Architecture to Support Arcade Game Playing
First, we explain the Iceblox game, which has its origin in the Pengo game. After carefully listing requirements on game playing, the contents of plans, their execution and planning problem generation, we design a set of benchmarks to select good playing candidates among currently available PDDL-based planners. We eventually selected two planners which are able to play the Iceblox video game we...
متن کاملClassical Planning with Simulators: Results on the Atari Video Games
The Atari 2600 games supported in the Arcade Learning Environment [Bellemare et al., 2013] all feature a known initial (RAM) state and actions that have deterministic effects. Classical planners, however, cannot be used off-the-shelf as there is no compact PDDL-model of the games, and action effects and goals are not known a priori. Indeed, there are no explicit goals, and the planner must sele...
متن کاملClassical Planning in Deep Latent Space: From Unlabeled Images to PDDL (and back)
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although recent work in deep learning has achieved impressive results in many fields, the knowledge is encoded in a subsymbolic representation which cannot be directly used by symbolic systems such as planners. We propose...
متن کاملAn Empirical Comparison of PDDL-based and ASP-based Task Planners
General purpose planners enable AI systems to solve many different types of planning problems. However, many different planners exist, each with different strengths and weaknesses, and there are no general rules for which planner would be best to apply to a given problem. In this paper, we empirically compare the performance of state-of-the-art planners that use either the Planning Domain Descr...
متن کاملTranslating Single-Player GDL into PDDL
In the single-agent case general game playing and action planning are two related topics, so that one might hope to use the established planners to improve the handling of general single-player games. However, both come with their own description language, GDL and PDDL, respectively. In this paper we propose a way to translate single-player games described in GDL to PDDL planning tasks and prov...
متن کامل