Fundamental of Reinforcement Learning
Preface
Cover
1. Introduction
What is Reinforcement Learning
History
Example
2. Markov Decision Process
MDP
Value Function
3. Bellman Equation
Bellman Expectation Equation
Bellman Optimality Equation
4. Dynamic Programming
Policy Iteration
Value Iteration
Example
5. Monte-Carlo Learning
Monte-Carlo Prediction
Monte-Carlo Control
6. Temporal Difference Learning
TD Prediction
TD Control
Eligibility Traces
7. Off-Policy Control
Importance Sampling
Q Learning
8. Value Function Approximation
Value function Approximation
Stochastic Gradient Descent
Learning with Function Approximator
9. DQN(Deep Q - Networks)
Neural Network
Deep Q Networks
10. Policy Gradient
Policy Gradient
Finite Difference Policy Gradient
Monte-Carlo Policy Gradient : REINFORCE
Actor-Critic Policy Gradient
Powered by
GitBook
9. DQN(Deep Q - Networks)
DQN
1. Neural Network
2. Deep Q Networks
results matching "
"
No results matching "
"