Industrial RL applications and challenges.
mediumAnswer
- Real applications: data center cooling (DeepMind 40% reduction), chip floorplan (DeepMind Nature 2021), advertising bidding, portfolio optimization, drug discovery (design molecules), catalyst design, tokamak plasma control (DeepMind + EPFL).
- Challenges: (1) sample efficiency (real interactions expensive).
- (2) Safety constraints.
- (3) Distribution shift between training and deployment.
- (4) Reward specification hard.
- Mostly offline RL + simulation + careful validation.
Check yourself — multiple choice
- Random
- Data center cooling / chip floorplan / advertising / portfolio / drug discovery / tokamak plasma; challenges: sample eff + safety + drift + reward specification; offline RL + sim + validation
- Only games
- Not real
Industrial RL: DC cooling / floorplan / ads / drugs / tokamak; sim + offline + safety.
#applications
Practise Reinforcement Learning
214 interview questions in this topic.