Multi-objective Robust Strategy Synthesis for Interval Markov Decision Processes.
Ernst Moritz HahnVahid HashemiHolger HermannsMorteza LahijanianAndrea TurriniPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- multi objective
- optimal policy
- finite state
- policy iteration
- state space
- transition matrices
- reinforcement learning
- dynamic programming
- evolutionary algorithm
- infinite horizon
- average reward
- genetic algorithm
- finite horizon
- reachability analysis
- decision processes
- decision theoretic planning
- factored mdps
- reinforcement learning algorithms
- partially observable
- average cost
- model based reinforcement learning
- multi objective optimization
- planning under uncertainty
- partially observable markov decision processes
- state abstraction
- discounted reward
- markov decision process
- machine learning
- risk sensitive
- particle swarm optimization
- optimal strategy
- semi markov decision processes