Login / Signup

More for Less: Safe Policy Improvement With Stronger Performance Guarantees.

Patrick WienhöftMarnix SuilenThiago D. SimãoClemens DubslaffChristel BaierNils Jansen
Published in: CoRR (2023)
Keyphrases
  • significant improvement
  • neural network
  • real world
  • information retrieval
  • artificial intelligence
  • computer vision
  • special case
  • np hard
  • infinite horizon
  • asymptotically optimal
  • policy search