- Reinforcement Learning with TensorFlow
- Sayon Dutta
- 107字
- 2021-08-27 18:51:57
Optimality criteria
The optimality criteria are a measure of goodness of fit of the model created over the data. For example, in supervised classification learning algorithms, we have maximum likelihood as the optimality criteria. Thus, on the basis of the problem statement and objective optimality criteria differs. In reinforcement learning, our major goal is to maximize the future rewards. Therefore, we have two different optimality criteria, which are:
- Value function: To quantify a state on the basis of future probable rewards
- Policy: To guide an agent on what action to take in a given state
We will discuss both of them in detail in the coming topics.
推薦閱讀
- 工業(yè)機(jī)器人虛擬仿真實(shí)例教程:KUKA.Sim Pro(全彩版)
- PowerShell 3.0 Advanced Administration Handbook
- 控制與決策系統(tǒng)仿真
- 樂(lè)高創(chuàng)意機(jī)器人教程(中級(jí) 下冊(cè) 10~16歲) (青少年iCAN+創(chuàng)新創(chuàng)意實(shí)踐指導(dǎo)叢書)
- 永磁同步電動(dòng)機(jī)變頻調(diào)速系統(tǒng)及其控制(第2版)
- 機(jī)器人編程實(shí)戰(zhàn)
- CentOS 8 Essentials
- 電腦主板現(xiàn)場(chǎng)維修實(shí)錄
- Hadoop應(yīng)用開(kāi)發(fā)基礎(chǔ)
- 單片機(jī)C語(yǔ)言程序設(shè)計(jì)完全自學(xué)手冊(cè)
- 從零開(kāi)始學(xué)SQL Server
- 精通LabVIEW程序設(shè)計(jì)
- Mastering MongoDB 3.x
- 空間機(jī)器人智能感知技術(shù)
- 玩機(jī)器人 學(xué)單片機(jī)