Login / Signup
A Fully Polynomial Time Approximation Scheme for Constrained MDPs Under Local Transitions.
Majid Khonji
Published in:
CDC (2023)
Keyphrases
</>
markov decision processes
reinforcement learning
finite horizon
state space
factored mdps
state transitions
optimal policy
machine learning
single item
search algorithm
infinite horizon
average cost
planning under uncertainty
markov decision problems