We introduce the Adaptive Skills, Adaptive Partitions (ASAP) algorithm that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them to solve a Markov decision process. ASAP is initially provided with a misspecified hierarchical model and is able to correct this model and learn a near-optimal set of skills to solve a given task. We believe that (1) and (2) are the core components necessary for a truly general skill learning framework, which is a key building block needed to scale up to lifelong learning agents. ASAP is also able to solve related new tasks simply by adapting where it applies its existing learned skills. We prove that ASAP converges to a local optimum under natural conditions. Finally, our extensive experimental results, which include a RoboCup domain, demonstrate the ability of ASAP to learn where to reuse skills as well as solve multiple tasks with considerably less experience than solving each task from scratch.
from cs.AI updates on arXiv.org http://ift.tt/1KcDjDb
via IFTTT
No comments:
Post a Comment