Reinforcement Learning Flashcards
7 cards from real Machine Learning practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Reinforcement Learning flashcards as text
What is the primary goal of a reinforcement learning agent?
Answer: To maximize cumulative reward over time
An RL agent learns by interacting with an environment to maximize the total cumulative reward it receives over time.
What does the reward signal represent in reinforcement learning?
Answer: Immediate scalar feedback indicating how good an action was
The reward signal provides immediate scalar feedback to the agent, indicating the desirability of the action taken in the current state.
In reinforcement learning, what is an 'episode'?
Answer: A complete sequence from the initial state to a terminal state
An episode is a complete sequence of interactions from the starting state to a terminal or goal state in the environment.
How does reinforcement learning fundamentally differ from supervised learning?
Answer: RL learns from environment interaction and reward signals, not labeled examples
Unlike supervised learning which uses labeled input-output pairs, RL agents learn from interactions with an environment using reward signals as feedback.
What is a policy in reinforcement learning?
Answer: A mapping from states to actions (or action probabilities) that defines agent behavior
A policy defines the agent's behavior by mapping states to actions or probabilities of actions, determining what the agent does in each situation.
What does the state-value function V(s) represent in RL?
Answer: The expected cumulative discounted reward starting from state s under the current policy
The value function V(s) estimates the expected total discounted reward an agent can accumulate starting from state s and following its current policy.
What is the exploration-exploitation tradeoff in reinforcement learning?
Answer: Choosing between trying new actions to discover better strategies versus using known good actions
The exploration-exploitation tradeoff involves balancing the need to explore new actions to discover better strategies versus exploiting known good actions to maximize reward.
How this page was made: written with AI tools and published by Nathan Beja, founder of Practice Test Geeks, who is responsible for its content. We have not yet matched this exam's facts to an official source, so confirm fees, dates and rules with the exam body. Not reviewed by a subject-matter expert. Editorial policy