- Keras Reinforcement Learning Projects
- Giuseppe Ciaburro
- 154字
- 2021-08-13 15:26:02
Reinforcement learning
Reinforcement learning aims to create algorithms that can learn and adapt to environmental changes. This programming technique is based on the concept of receiving external stimuli, the nature of which depends on the algorithm choices. A correct choice will involve a reward, while an incorrect choice will lead to a penalty. The goal of the system is to achieve the best possible result, of course.
In supervised learning, there is a teacher that tells the system the correct output (learning with a teacher). This is not always possible. Often, we have only qualitative information (sometimes binary, right/wrong, or success/failure).
The information available is called reinforcement signals. But the system does not give any information on how to update the agent's behavior (that is, weights). You cannot define a cost function or a gradient. The goal of the system is to create smart agents that have machinery able to learn from their experience.
- 機(jī)器學(xué)習(xí)實戰(zhàn):基于Sophon平臺的機(jī)器學(xué)習(xí)理論與實踐
- 大數(shù)據(jù)管理系統(tǒng)
- 大學(xué)計算機(jī)基礎(chǔ):基礎(chǔ)理論篇
- PostgreSQL Administration Essentials
- Data Wrangling with Python
- The Python Workshop
- 貫通Java Web開發(fā)三劍客
- Photoshop行業(yè)應(yīng)用基礎(chǔ)
- 計算機(jī)組網(wǎng)技術(shù)
- 軟件工程及實踐
- Word 2007,Excel 2007辦公應(yīng)用融會貫通
- Xilinx FPGA高級設(shè)計及應(yīng)用
- 智能+:制造業(yè)的智能化轉(zhuǎn)型
- Eclipse RCP應(yīng)用系統(tǒng)開發(fā)方法與實戰(zhàn)
- JSP網(wǎng)絡(luò)開發(fā)入門與實踐