Login / Signup
Joint learning of reward machines and policies in environments with partially known semantics.
Christos K. Verginis
Cevahir Köprülü
Sandeep Chinchali
Ufuk Topcu
Published in:
Artif. Intell. (2024)
Keyphrases
</>
reinforcement learning
learning machines
learning algorithm
learning process
prior knowledge
supervised learning
logic programming
dynamic environments
learning systems
learning problems
real world
belief revision
inductive inference
policy gradient methods