EasyDeepLearn

Why is RL hard for autonomous driving?

hard

Answer

  • (1) Safety: cannot explore in real traffic.
  • (2) Long-tail rare events matter (fatal edge cases).
  • (3) Multi-agent interactions (other drivers, pedestrians) with non-stationary policies.
  • (4) Partial observability.
  • (5) Reward specification difficulty.
  • Most industry uses SL / imitation learning + planning stack (Waymo, Cruise).
  • RL used mostly in simulation for policy fine-tuning, closed-loop training.
  • Recent: Tesla's neural planners are hybrid IL + RL.
Check yourself — multiple choice
  • Same as games
  • Safety (no exploration) + long-tail edge cases + multi-agent non-stationary + partial obs + reward specification hard; industry uses SL/IL + planning; RL in sim + Tesla hybrid IL+RL
  • Random
  • Not real

AD hard: safety + long-tail + multi-agent + partial obs; industry SL/IL + sim RL.

#applications#safety

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions