Multi-objective Discounted Reward Verification in Graphs and MDPs.
Krishnendu ChatterjeeVojtech ForejtDominik WojtczakPublished in: LPAR (2013)
Keyphrases
- discounted reward
- multi objective
- markov decision processes
- average reward
- policy iteration
- optimal policy
- evolutionary algorithm
- state and action spaces
- multi objective optimization
- reinforcement learning
- genetic algorithm
- objective function
- multiple objectives
- state space
- finite state
- model checking
- long run
- model free
- partially observable
- hierarchical reinforcement learning
- markov decision problems
- pareto optimal
- dynamic programming
- planning under uncertainty
- machine learning
- decision making
- action space
- reinforcement learning algorithms
- least squares