COMP9444 Neural Networks and Deep Learning

Quiz 7 (Reinforcement Learning)

1. Explain the difference between the following paradigms, in terms of what is presented to the agent, and what the agent aims to do:
   • Supervised Learning
   • Unsupervised Learning
   • Reinforcment Learning

2. Describe the elements (sets and functions) that are needed to give a formal description of a reinforcement learning environment. What is the difference between a deterministic environment and a stochastic environment?

3. Name three different models of optimality in reinforcement learning, and give a formula for calculating each one.

4. What is the definition of:
   1. the optimal policy
   2. the value function
   3. the Q-function?

5. Assuming a stochastic environment, discount factor γ and learning rate of η, write the equation for
   1. Temporal Difference learning TD(0)
   2. Q-Learning
   Remember to define any symbols you use.