تقرير
Training Agents using Upside-Down Reinforcement Learning
| العنوان: | Training Agents using Upside-Down Reinforcement Learning |
|---|---|
| المؤلفون: | Srivastava, Rupesh Kumar, Shyam, Pranav, Mutz, Filipe, Jaśkowski, Wojciech, Schmidhuber, Jürgen |
| سنة النشر: | 2019 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Robotics |
| الوصف: | We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or search for an optimal policy. Instead, it trains agents to follow commands such as "obtain so much total reward in so much time." Many of its general principles are outlined in a companion report; the goal of this paper is to develop a practical learning algorithm and show that this conceptually simple perspective on agent training can produce a range of rewarding behaviors for multiple episodic environments. Experiments show that on some tasks UDRL's performance can be surprisingly competitive with, and even exceed that of some traditional baseline algorithms developed over decades of research. Based on these results, we suggest that alternative approaches to expected reward maximization have an important role to play in training useful autonomous agents. Comment: Extends NeurIPS 2019 Deep Reinforcement Learning workshop presentation |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1912.02877 |
| رقم الأكسشن: | edsarx.1912.02877 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |