Skip to content

Latest commit

 

History

History
41 lines (21 loc) · 767 Bytes

reinforcement-learning.md

File metadata and controls

41 lines (21 loc) · 767 Bytes

Reinforcement Learning

Overview

Overview

Brief History

Brief History

Side Note: Reinforcement is a misused term, because all we care is to maximize rewards.

Reinforcement Learning Approaches

RL Approaches

Q Value Function

Q Value Function

Estimating Q

Estimating Q

Estimating Q 2

Q-Learning Convergence

Q-Learning Convergence

Choosing Actions

Choosing Actions

Greedy Exploration

Greedy Exploration

Summary

Summary