EasyDeepLearn

When does tabular Q-learning fail in practice?

medium

Answer

  • (1) State space too large: even discretized MazeGrid > 1M states makes tabular infeasible.
  • (2) Continuous features: discretization fights curse of dimensionality.
  • (3) Function structure across states unexploited (Q for nearby states should be similar → NN generalizes; tabular treats them independently).
  • (4) Slow: no generalization means each state must be visited separately.
  • Every real RL problem > toy uses function approximation (usually NN).
Check yourself — multiple choice
  • Never fails
  • Fails when state space large / continuous / structured (NN can share params, tabular can't) — real RL uses function approximation
  • Random
  • Only supervised

Tabular fails: large / continuous / structured states — needs FA.

#theory#deep-rl

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions