EasyDeepLearn

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

easy

Answer

  • An agent observes a state s from the environment, picks an action a via its policy π(as)\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.
Check yourself — multiple choice
  • The policy maps rewards to states
  • The policy maps states to a distribution over actions
  • The policy is the same as the value function
  • RL requires labeled examples

A policy is π(as)\pi(a \mid s) — a distribution over actions given a state.

#fundamentals

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions