Login / Signup
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods.
Riccardo De Santi
Manish Prajapat
Andreas Krause
Published in:
CoRR (2024)
Keyphrases
</>
reinforcement learning
piecewise linear
markov decision processes
control problems
neural network
objective function
preprocessing
computational cost
state space
optimal policy
machine learning methods
temporal difference
global features