Bi-objective Lexicographic Optimization in Markov Decision Processes with Related Objectives.
Damien Busatto-GastonDebraj ChakrabortyAnirban MajumdarSayan MukherjeeGuillermo A. PérezJean-François RaskinPublished in: ATVA (1) (2023)
Keyphrases
- markov decision processes
- bi objective
- multiple objectives
- multi objective
- state space
- multi objective evolutionary algorithms
- reinforcement learning
- finite state
- optimal policy
- dynamic programming
- transition matrices
- multi objective optimization
- policy iteration
- global optimization
- optimization algorithm
- average reward
- finite horizon
- decision theoretic planning
- model based reinforcement learning
- action space
- planning under uncertainty
- infinite horizon
- knapsack problem
- average cost
- action sets
- pareto optimal
- combinatorial optimization
- neural network
- efficient solutions
- shortest path problem
- evolutionary algorithm
- optimization problems
- partially observable
- long run