Login / Signup
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling.
Utsav Singh
Wesley A. Suttle
Brian M. Sadler
Vinay P. Namboodiri
Amrit Singh Bedi
Published in:
CoRR (2024)
Keyphrases
</>
hierarchical reinforcement learning
reinforcement learning
state abstraction
model free
hidden markov models
neural network
machine learning
probabilistic model
state space
markov chain
markov decision processes
action selection