ML-Markov Decision Processes (MDPs)

In Reinforcement Learning, Markov Decision Processes (MDPs) are used to model:

• Unsupervised learning tasks

• Supervised learning tasks

• Semi-supervised learning tasks

• Decision-making under uncertainty

What is the primary assumption made in Markov Decision Processes (MDPs)?

• The environment is deterministic and fully observable.

• The environment is deterministic, but partially observable.

• The environment is stochastic and fully observable.

• The environment is stochastic and partially observable.

In the context of MDPs, what does the term "state" represent?

• The set of all possible actions an agent can take

• The sequence of actions taken by the agent

• The representation of the agent's policy

• The description of the environment at a specific time

What is the role of the "action" in the Markov Decision Processes (MDPs) framework?

• To represent the state of the environment

• To represent the current reward received by the agent

• To represent the transition from one state to another

• To represent the policy followed by the agent

In Markov Decision Processes (MDPs), what is the "transition probability"?

• The immediate reward received by the agent for taking an action

• The probability distribution of actions in a given state

• The probability of transitioning from one state to another after taking an action

• The measure of how good the agent's policy is

What does the term "policy" represent in the context of Markov Decision Processes (MDPs)?

• The measure of how good the agent's decisions are

• The immediate reward received by the agent for taking an action

• The probability distribution over actions given a certain state

• The set of rules governing the agent's behavior

What is the objective of the agent in the Markov Decision Processes (MDPs) framework?

• To maximize the number of actions taken

• To find the optimal policy that maximizes the cumulative rewards

• To classify data into different categories

• To minimize the difference between predicted and actual values

The Bellman equation in Markov Decision Processes (MDPs) expresses:

• The optimal policy of the agent

• The value function for each state

• The set of all possible actions the agent can take

• The reward function

What does the "value function" in Markov Decision Processes (MDPs) represent?

• The quality of the training data

• The probability of taking a certain action

• The expected cumulative reward for being in a certain state

• The percentage of correct predictions made by the agent

The "optimal value function" in Markov Decision Processes (MDPs) represents:

• The highest immediate reward received in each state

• The expected cumulative reward for each action in each state

• The expected cumulative reward for following the optimal policy from each state

• The maximum number of actions an agent can take in the environment