التفاصيل البيبلوغرافية
| العنوان: |
Hindsight Experience Replay |
| المؤلفون: |
Andrychowicz, Marcin, Wolski, Filip, Ray, Alex, Schneider, Jonas, Fong, Rachel, Welinder, Peter, McGrew, Bob, Tobin, Josh, Abbeel, Pieter, Zaremba, Wojciech |
| سنة النشر: |
2017 |
| المجموعة: |
Computer Science |
| مصطلحات موضوعية: |
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Computer Science - Robotics |
| الوصف: |
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum. We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in each case using only binary rewards indicating whether or not the task is completed. Our ablation studies show that Hindsight Experience Replay is a crucial ingredient which makes training possible in these challenging environments. We show that our policies trained on a physics simulation can be deployed on a physical robot and successfully complete the task. |
| نوع الوثيقة: |
Working Paper |
| URL الوصول: |
http://arxiv.org/abs/1707.01495 |
| رقم الانضمام: |
edsarx.1707.01495 |
| قاعدة البيانات: |
arXiv |