با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
دسته بندی:
یادگیری تقویتی - Reinforcement-Learning
سال انتشار:
2020
عنوان انگلیسی مقاله:
Improving robot dual-system motor learning with intrinsically motivated meta-control and latent-space experience imagination
ترجمه فارسی عنوان مقاله:
بهبود یادگیری حرکتی سیستم دوگانه ربات با انگیزه ذاتی متا کنترل و تجربه فضای پنهان تخیلی
منبع:
Sciencedirect - Elsevier - Robotics and Autonomous Systems, 133 (2020) 103630. doi:10.1016/j.robot.2020.103630
نویسنده:
Muhammad Burhan Hafez ∗, Cornelius Weber, Matthias Kerzel, Stefan Wermter
چکیده انگلیسی:
Combining model-based and model-free learning systems has been shown to improve the sample
efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to
consider the reliability of the learned model when it is applied to make multiple-step predictions,
resulting in a compounding of prediction errors and performance degradation. In this paper, we present
a novel dual-system motor learning approach where a meta-controller arbitrates online between
model-based and model-free decisions based on an estimate of the local reliability of the learned
model. The reliability estimate is used in computing an intrinsic feedback signal, encouraging actions
that lead to data that improves the model. Our approach also integrates arbitration with imagination
where a learned latent-space model generates imagined experiences, based on its local reliability, to
be used as additional training data. We evaluate our approach against baseline and state-of-the-art
methods on learning vision-based robotic grasping in simulation and real world. The results show
that our approach outperforms the compared methods and learns near-optimal grasping policies in
dense- and sparse-reward environments.
Keywords: Meta-control | Arbitration | Experience imagination | Intrinsic motivation | Reinforcement learning | Robotic grasping
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0