Hierarchical Width-Based Planning and Learning
| Autor: | Junyent Barbany, Miquel, Gómez, Vicenç, Jonsson, Anders, 1973 |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Learning To Improve The Effectiveness Of Planning & Scheduling Systems Artificial Intelligence (cs.AI) Computer Science - Artificial Intelligence Reinforcement Learning Using Planning (model-based Bayesian Deep Etc.) Applications That Involve A Combination Of Learning With Planning Or Scheduling Theoretical Aspects Of Planning And Learning |
| Zdroj: | Proceedings of the International Conference on Automated Planning and Scheduling. 31:519-527 |
| ISSN: | 2334-0843 2334-0835 |
| DOI: | 10.1609/icaps.v31i1.15999 |
| Popis: | Comunicació presentada a: ICAPS2021 celebrat del 2 a 13 d'agost de 2021 a Guangzhou, Xina. Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the state-space, but exponentially in the problem width. In practice, running the algorithm with a width larger than 1 is computationally intractable, prohibiting IW from solving higher width problems. In this paper, we present a hierarchical algorithm that plans at two levels of abstraction. A high-level planner uses abstract features that are incrementally discovered from low-level pruning decisions. We illustrate this algorithm in classical planning PDDL domains as well as in pixel-based simulator domains. In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2. For pixel-based domains, we show how in combination with a learned policy and a learned value function, the proposed hierarchical IW can outperform current flat IW-based planners in Atari games with sparse rewards. V. Gómez has received funding from “La Caixa” Foundation (100010434), under the agreement LCF/PR/PR16/51110009 and is supported by the Ramon y Cajal program RYC-2015-18878 (AEI/MINEICO/FSE,UE). A. Jonsson is partially supported by Spanish grants PID2019-108141GB-I00 and PCIN-2017-082. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|