Reinforcement Learning 4: Dynamic programming

Описание к видео Reinforcement Learning 4: Dynamic programming

Slides: https://cwkx.github.io/data/teaching/...
Colab: https://colab.research.google.com/gis...
Twitter:   / cwkx  
Next video:    • Reinforcement Learning Lectures  

Introduction
definition
examples
planning in an MDP
Policy evaluation
definition
synchronous algorithm
Policy iteration
policy improvement
definition
modified policy iteration
Value iteration
definition
summary and extensions

#reinforcementlearning #dynamicprogramming #MDPs #policyevaluation #policyiteration #valueiteration #planning

Комментарии

Информация по комментариям в разработке