Login / Signup

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping.

Lina MezghaniSainbayar SukhbaatarPiotr BojanowskiAlessandro LazaricKarteek Alahari
Published in: CoRR (2023)
Keyphrases
  • neural network
  • learning process
  • supervised learning
  • learning tasks
  • inductive learning
  • reward shaping
  • learning algorithm
  • sufficient conditions
  • solving problems