EasyDeepLearn

Potential-based reward shaping — why is it safe?

hard

Answer

  • Ng, Harada, Russell 1999.
  • Add r'(s, a, s') = r(s, a, s') + γΦ(s') - Φ(s).
  • Any potential function Φ is safe: doesn't change optimal policy (only value baseline).
  • Because Σt{\Sigma}_{t} γt{\gamma}^{t} (γΦ(st+1)    Φ(st))({\gamma}{\Phi}(s_{t + 1})\; - \;{\Phi}(s_{t})) telescopes to  Φ(s0)  +  γT\mathrm{to}\; - {\Phi}(s_{0})\; + \;{\gamma}^{T} Φ(sT){\Phi}(s_{T}) → same argmax over policies.
  • Enables safe reward engineering without changing task.
  • Standard technique in robotics reward design.
Check yourself — multiple choice
  • Random
  • r' = r + γΦ(s') - Φ(s); telescopes → same optimal policy for any Φ (only value baseline changes); safe reward engineering without altering task — Ng-Harada-Russell 1999
  • Same as shaping
  • Not real

Potential shaping: γΦ(s') - Φ(s) telescopes; preserves optimal policy.

#reward-design#theory

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions