Graph-Based Reductions for Parametric and Weighted MDPs.

Kasper Engelen Guillermo A. Pérez Shrisha Rao

Published in: CoRR (2023)

Keyphrases

markov decision processes
reinforcement learning
graph model
finite horizon
state space
optimal policy
reward function
factored mdps
dynamic programming
weighted sum
parametric models
multiple agents
decision diagrams
decision theoretic planning
semi markov decision processes