سال انتشار:
2020
عنوان انگلیسی مقاله:
Additional planning with multiple objectives for reinforcement learning
ترجمه فارسی عنوان مقاله:
برنامه ریزی اضافی با چندین هدف برای یادگیری تقویتی
منبع:
Sciencedirect - Elsevier - Knowledge-Based Systems, 193 (2020) 105392. doi:10.1016/j.knosys.2019.105392
نویسنده:
Anqi Pan a,b, Wenjun Xu c,d, Lei Wange, Hongliang Ren c,∗
چکیده انگلیسی:
Most control tasks have multiple objectives that need to be achieved simultaneously, while the
reward definition is the weighted combination of all objects to determine one optimal policy. This
configuration has a limitation in exploration flexibility and presents difficulty in reaching a satisfied
terminate condition. Although some multi-objective reinforcement learning (MORL) methods have
been presented recently, they concentrate on obtaining a set of compromising options rather than
one best-performed strategy. On the other hand, the existing policy-improve methods have rarely
emphasized on solving multiple objectives circumstances. Inspired by the enhanced policy search
methods, an additional planning technique with multiple objectives for reinforcement learning is
proposed in this paper, which is denoted as RLAP-MOP. This method provides opportunities to evaluate
parallel requirements at the same time and suggests several optimal feasible actions to improve longterm
performance further. Meanwhile, the short-term planning adopted in this paper has advantages
in maintaining safe trajectories and building more accurate approximate models, which contributes
to accelerating the training program. For comparison, an RLAP with single-objective optimization is
also introduced in theoretical and experimental studies. The proposed techniques are investigated
on a multi-objective cartpole environment and a soft robotic palpation task. The superiorities in the
improved return values and learning stability prove that the multiple objectives based additional
planning is a promising assistant to improve reinforcement learning.
Keywords: Reinforcement learning | Multi-objective | Robotic control
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0