AI and ML for Finance Practitioners

Agent: The program you train, with the goal of doing a job you specify.
Action: A move made by the agent, which causes a status change in the environment.
Environment: The world, real or virtual, in which the agent performs actions.
Rewards: The evaluation of an action, which can be positive or negative.”

True

False

Question 1 of 3

Question 2 of 3

2. What is the “agent” of a Reinforcing Learning task where a robot can teach itself to move more effectively by adapting its policy based on the rewards it receives?

Task:Controlling A Walking Robot.
Agent:

\boxed{?}

Environment: The real world.
Action: One out of four moves: (1) forward; (2) backward; (3) left, and (4) right.
Reward: Positive when it approaches the target destination; negative when it wastes time, goes in the wrong direction or falls down.

The program controlling only the speed of the robot.

The program controlling the whole walking robot.

The program controlling only the direction of the robot.

Question 2 of 3

Question 3 of 3

3. Which of these statements incorrectly describes the differences between RL and supervised / unsupervised learning?

Statement I:“Static (supervised/unsupervised) Vs.Dynamic (RL)
– Static: The goal of supervised and unsupervised learning is to search for and learn about patterns in training data, which is quite static.
– Dynamic: RL is about developing a policy that tells an agent which action to choose at each step — making it more dynamic. “

Statement II:” RL is a Multiple-Decision Process while supervised learning is a single-decision process
– Reinforcement Learning is a multiple-decision process: it forms a decision-making chain through the time required to finish a specific job.
– Supervised learning is a single-decision process: one instance, one prediction.”
I
II
I and II
None

Question 3 of 3