EasyDeepLearn
← All categories
Reinforcement Learning
Interview · flashcards

Reinforcement Learning

MDPs, exploration, policy vs value methods, and modern actor-critic algorithms.

← LessonStart quiz →
easyfundamentals

Define the RL setting: agent, environment, state, action, reward, policy.

Click, press Space or use the button below to reveal the answer
Interview-style answer
  • An agent observes a state s from the environment, picks an action a via its policy π(a∣s)\pi(a \mid s), receives a reward r and a new state s'.
  • The goal is to maximize the expected cumulative discounted reward (return).
  • Formalized as a Markov Decision Process (S, A, P, R, gamma).
  • The agent learns pi (or a value function) from interaction with the environment.
Click again to flip back
1 / 214

Shortcuts: Space/Enter flip · ← / → navigate · K = known · R = review