Interval Markov Decision Processes with Multiple Objectives: From Robust Strategies to Pareto Curves.
Ernst Moritz HahnVahid HashemiHolger HermannsMorteza LahijanianAndrea TurriniPublished in: ACM Trans. Model. Comput. Simul. (2019)
Keyphrases
- markov decision processes
- multiple objectives
- multi objective
- multi objective optimization
- pareto optimal
- multiobjective optimization
- state space
- reinforcement learning
- finite state
- dynamic programming
- transition matrices
- policy iteration
- optimal policy
- decision theoretic planning
- planning under uncertainty
- average cost
- reachability analysis
- finite horizon
- optimization algorithm
- knapsack problem
- factored mdps
- evolutionary algorithm
- reinforcement learning algorithms
- partially observable
- state and action spaces
- infinite horizon
- particle swarm optimization
- objective function
- average reward
- heuristic search
- action sets
- model based reinforcement learning
- partially observable markov decision processes
- reward function
- neural network
- discounted reward
- machine learning