Markov Decision Processes For Multi-Objective Satellite Task Planning.
Duncan EddyMykel J. KochenderferPublished in: CoRR (2019)
Keyphrases
- differential evolution
- markov decision processes
- multi objective
- evolutionary algorithm
- multi objective optimization
- macro actions
- decision theoretic planning
- planning under uncertainty
- partially observable
- genetic algorithm
- nsga ii
- state space
- finite state
- optimal policy
- transition matrices
- reinforcement learning
- dynamic programming
- finite horizon
- planning problems
- reachability analysis
- policy iteration
- probabilistic planning
- markov decision process
- average reward
- factored mdps
- reinforcement learning algorithms
- infinite horizon
- multiple objectives
- ai planning
- objective function
- action space
- model based reinforcement learning
- markov decision problems
- reward function
- action sets
- partially observable markov decision processes
- pareto optimal
- decision theoretic
- decision processes
- heuristic search
- decision making
- neural network
- state and action spaces
- blocks world
- average cost
- decision theory
- sufficient conditions
- domain independent