Bi-Objective Lexicographic Optimization in Markov Decision Processes with Related Objectives.
Damien Busatto-GastonDebraj ChakrabortyAnirban MajumdarSayan MukherjeeGuillermo A. PérezJean-François RaskinPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- bi objective
- multiple objectives
- multi objective
- finite state
- reinforcement learning
- optimal policy
- multi objective evolutionary algorithms
- policy iteration
- state space
- transition matrices
- optimization algorithm
- finite horizon
- decision theoretic planning
- dynamic programming
- multi objective optimization
- efficient solutions
- average cost
- average reward
- partially observable
- planning under uncertainty
- optimization problems
- combinatorial optimization
- knapsack problem
- global optimization
- pareto optimal
- network design
- reward function
- action sets
- action space
- markov decision process
- evolutionary algorithm
- machine learning
- objective function
- graphical models
- special case
- infinite horizon
- cost function
- probability distribution
- ant colony optimization
- particle swarm optimization
- linear programming