Reinforcement Learning 101

Any new subject can be learned in the same way as we learn any new language (Learning new vocabulary → Understanding Language syntax → Conversing with localites)

Objective of reinforcement learning is to implement automation, optimization and discovery with minimal human intervention.

In this blog I will give an introduction to Reinforcement learning vocab

1. Agent
1. Single
2. Multi
1. Independent Q-learning
2. CTDE
3. MADDPG
2. Environment
1. Stationary
2. Non-Stationary
3. State
4. Action
5. Episode, Visit
6. Reward
1. Long Term
2. Short Term
7. Markov Decision Process
8. Bellman Equation
9. Transition Probability
10. Discounting Factor
11. Policy
12. Value Function
1. State
1. Monte Carlo Method to learn
2. Action
13. Model
1. Free
1. Q-Learning
2. SARSA
   
3. DQN
2. Based
1. Dyna-Q
2. Monte Carlo Tree Search
3. PILCO
3. Policy Gradient Method
1. REINFORCE
14. Iteration
1. Policy
2. Value
15. Evaluation
1. Policy
16. Improvement
1. Policy
17. Exploration vs Eploitation
1. Exporation Strategies
18. Initialization
19. Termination
20. Actor Critic Methods
    

I'll keep updating this blog whenever I have time