Reinforcement Learning 7: Function approximation

Описание к видео Reinforcement Learning 7: Function approximation

Slides: https://cwkx.github.io/data/teaching/...
Code: https://github.com/higgsfield/RL-Adve...
Twitter:   / cwkx  
Next video:    • Reinforcement Learning Lectures  

Function approximation
- introduction
- definition
- challenges
Incremental methods
- SGD for prediction
- SGD for control
- convergence
Batch learning
- experience replay
- model freezing with double Q-learning

#reinforcementlearning #experiencereplay #functionapproximation #Qlearning #batchlearning #incrementalmethods

Комментарии

Информация по комментариям в разработке