Login / Signup
On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning.
Rohan Subramani
Marcus Williams
Max Heitmann
Halfdan Holm
Charlie Griffin
Joar Skalse
Published in:
CoRR (2023)
Keyphrases
</>
reinforcement learning
computational properties
state space
machine learning
optimal policy
function approximation
neural network
high level
knowledge representation
learning process
markov decision processes
reinforcement learning algorithms
markov decision process