Reinforcement Learning - Temporal Difference Learning

1 Reinforcement Learning - Introduction to Reinforcement Learning

2 MCQ - In Reinforcement Learning, a software agent makes observations, takes actions within an environment, and receives rewards in return

3 MCQ - A policy is the algorithm used by software agent to determine its actions.

4 MCQs- Reinforcement learning is -

5 MCQs - Which of the following is true about reinforcement learning?

6 Reinforcement Learning - Introduction to OpenAI Gym

7 MCQ - OpenAI gym is a toolkit that provides wide variety of simulations to train agents in Reinforcement Learning

8 Reinforcement Learning - Credit Assignment Problem (Part I)

9 Reinforcement Learning - Credit Assignment Problem (Part II)

10 MCQ - An action advantage is the estimate of how much better or worse an action is compared to other possible actions, on average

11 MCQ -REINFORCE algorithms were introduced by Ronald Williams in

12 Reinforcement Learning - Markov Decision Processes

13 MCQ - Markov Chains are stochastic processes with no memory

14 MCQs - Hidden Markov Model is used in Reinforcement learning.

15 Reinforcement Learning - Value Iteration Algorithm, Q-Value

16 Reinforcement Learning - Temporal Difference Learning

17 Reinforcement Learning - Q-Learning

18 MCQ - Q-Learning algorithm is off-policy algorithm because

19 MCQ - DNN that estimates Q-Values is called Deep Q-Network (DQN)

20 MCQ - The Dueling DQN algorithm was introduced in yet another 2015 paper by

21 Reinforcement Learning - TF-Agents Library

22 MCQ - TF-Agents library is a Reinforcement Learning library based on TensorFlow