Finite-memory Strategies for Almost-sure Energy-MeanPayoff Objectives in MDPs.

Mohan Dantam Richard Mayr

Published in: CoRR (2024)

Keyphrases

markov decision processes
state and action spaces
reinforcement learning
energy consumption
factored mdps
energy minimization
memory requirements
random access
state space
optimal policy
data structure
energy saving
memory space
markov decision process
policy iteration
real time dynamic programming