Login / Signup

DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning.

Utsav SinghSouradip ChakrabortyWesley A. SuttleBrian M. SadlerVinay P. NamboodiriAmrit Singh Bedi
Published in: CoRR (2024)
Keyphrases
  • hierarchical reinforcement learning
  • reinforcement learning
  • machine learning
  • hidden markov models