The agent's strategy or plan of action that maps states to actions is called a

The agent's strategy or plan of action that maps states to actions is called a

• A. Value Function
• B. Policy
• C. Reward
• D. Action-Value Function

Answer: (B)

The idea being tested is what term describes the plan that tells the agent what to do in every state. That plan is a policy. In reinforcement learning, a policy is a mapping from states (or observations) to actions, outlining the agent’s behavior. It can be deterministic (one action for each state) or stochastic (a probability distribution over actions for each state). This distinguishes it from the value function, which assigns a numeric value to states (or state-action pairs) representing expected return under a policy, not the action rule itself. The reward is the immediate payoff received after an action, and the action-value function (Q-function) gives the expected return for taking a specific action in a state and then following a policy, which is a value estimate rather than the decision rule. So the agent’s strategy mapping states to actions is the policy.

The idea being tested is what term describes the plan that tells the agent what to do in every state. That plan is a policy. In reinforcement learning, a policy is a mapping from states (or observations) to actions, outlining the agent’s behavior. It can be deterministic (one action for each state) or stochastic (a probability distribution over actions for each state). This distinguishes it from the value function, which assigns a numeric value to states (or state-action pairs) representing expected return under a policy, not the action rule itself. The reward is the immediate payoff received after an action, and the action-value function (Q-function) gives the expected return for taking a specific action in a state and then following a policy, which is a value estimate rather than the decision rule. So the agent’s strategy mapping states to actions is the policy.